commit 853694f4684576815276f322b01dbdfd7726c835 Author: ModelHub XC Date: Thu Jun 25 06:43:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Vikhrmodels/salt-asr_speech_1_wav_1_tts_speech_3_text-10k Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8931902 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text + +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text + +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text +speechtokenizer/SpeechTokenizer.pt filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text +wavtokenizer/WavTokenizer_small_600_24k_4096.ckpt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..0173f52 --- /dev/null +++ b/README.md @@ -0,0 +1,152 @@ +--- +library_name: transformers +datasets: +- openslr/librispeech_asr +- parler-tts/libritts-r-filtered-speaker-descriptions +- llm-blender/mix-instruct +language: +- en +base_model: +- meta-llama/Llama-3.2-3B +--- + +**Inference**:
+ +```python +device = "cuda" + +n_codebooks_tts = 3 +n_codebooks_asr = 1 + +start_audio_token = "<|start_of_audio|>" +end_audio_token = "<|end_of_audio|>" +end_sequence_token = "<|end_of_text|>" + +base_model = "Vikhrmodels/salt-asr_speech_1_wav_1_tts_speech_3_text-10k" + + +def decode_tts(tokens, quantizer, n_codebooks, n_original_tokens, start_audio_token_id, end_audio_token_id): + # find start and end indices of audio tokens + start = torch.nonzero(tokens == start_audio_token_id) + end = torch.nonzero(tokens == end_audio_token_id) + + start = start[0, -1] + 1 if len(start) else 0 + end = end[0, -1] if len(end) else tokens.shape[-1] + + # subtract length of original vocabulary -> tokens in range [0, 1024) + audio_tokens = tokens[start:end] % n_original_tokens + reminder = audio_tokens.shape[-1] % n_codebooks + + if reminder: + # pad if last frame is incomplete + pad_tokens = torch.zeros(n_codebooks - reminder, device="cuda") + audio_tokens = torch.cat([audio_tokens, pad_tokens], dim=0) + + transposed = audio_tokens.view(-1, n_codebooks).t() + codes = transposed.view(n_codebooks, 1, -1).to(device) + + audio = quantizer.decode(codes).squeeze(0) + + del tokens + del audio_tokens + torch.cuda.empty_cache() + + return AudioSignal(audio.detach().cpu().numpy(), quantizer.sample_rate) + + +def infer_text_to_audio(text, model, tokenizer, quantizer, max_seq_length=1024, top_k=20): + text_tokenized = tokenizer(text, return_tensors="pt") + text_input_tokens = text_tokenized["input_ids"].to(device) + + soa = tokenizer(start_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + eoa = tokenizer(end_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + + text_tokens = torch.cat([text_input_tokens, soa], dim=1) + attention_mask = torch.ones(text_tokens.size(), device=device) + + output_audio_tokens = model.generate( + text_tokens, + attention_mask=attention_mask, + max_new_tokens=max_seq_length, + top_k=top_k, + do_sample=True, + temperature=0.1, + repetition_penalty=1.1, + length_penalty=1.2, + no_repeat_ngram_size=3, + ) + + audio_signal = decode_tts(output_audio_tokens[0], quantizer, 3, len(tokenizer), soa, eoa) + + return audio_signal + + +def infer_audio_to_text(audio_path, model, tokenizer, quantizer_speech, quantizer_wav, max_seq_length=1024, top_k=20): + audio_data, sample_rate = torchaudio.load(audio_path) + + audio = audio_data.view(1, -1).float().to(device) + bandwidth_id = torch.tensor([0]) + + codes_semantics = quantizer_speech.encode(audio.reshape(1, 1, -1)) + raw_semantic_tokens = codes_semantics + len(tokenizer) + raw_semantic_tokens = raw_semantic_tokens[:1].view(1, -1) + + _, codes = quantizer_wav.encode_infer(audio, bandwidth_id=bandwidth_id) + raw_acoustic_tokens = codes + len(tokenizer) + 1024 + raw_acoustic_tokens = raw_acoustic_tokens.view(1, -1) + + audio_tokens = torch.cat([raw_semantic_tokens, raw_acoustic_tokens], dim=1) + + soa = tokenizer(start_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + eoa = tokenizer(end_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + audio_tokens = torch.cat([soa, audio_tokens, eoa], dim=1) + tokens = torch.cat([audio_tokens], dim=1) + + attention_mask = torch.ones(tokens.size(), device=device) + + output_text_tokens = model.generate( + tokens, + attention_mask=attention_mask, + max_new_tokens=max_seq_length, + do_sample=True, + temperature=0.1, + top_p=0.9, + top_k=top_k, + ) + + output_text_tokens = output_text_tokens.cpu()[0] + output_text_tokens = output_text_tokens[output_text_tokens < tokenizer(start_audio_token)["input_ids"][-1]] + decoded_text = tokenizer.decode(output_text_tokens, skip_special_tokens=True) + + return decoded_text + + +tokenizer = AutoTokenizer.from_pretrained(base_model, cache_dir=".") +model = AutoModelForCausalLM.from_pretrained( + base_model, + cache_dir=".", + torch_dtype=torch.bfloat16, + attn_implementation="sdpa", + device_map={"": 0} +) + +quantizer_speech = SpeechTokenizer.load_from_checkpoint("speechtokenizer/config.json", + "speechtokenizer/SpeechTokenizer.pt") +quantizer_speech = quantizer_speech.eval().to(device) +codebook_size = quantizer_speech.quantizer.bins + +quantizer_wav = WavTokenizer.from_pretrained0802("wavtokenizer/config.yaml", + "wavtokenizer/WavTokenizer_small_600_24k_4096.ckpt") +quantizer_wav = quantizer_wav.to(device) + +text = ("Say 'COUNT NUMBERS FROM ONE TO TEN' with a male speaker delivers a very monotone and " + "low-pitched speech with a moderate speed in a setting with almost no noise, " + "creating a clear and quiet recording.") + +audio_signal = infer_text_to_audio(text, model, tokenizer, quantizer_speech, top_k=60) +audio_signal.write("output.wav") + +audio_path = "./input.wav" +generated_text = infer_audio_to_text(audio_path, model, tokenizer, quantizer_speech, quantizer_wav, top_k=10) +print(generated_text) +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..7209236 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "meta-llama/Llama-3.2-3B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.44.0", + "use_cache": true, + "vocab_size": 133379 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..55c226b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.44.0" +} diff --git a/inference.py b/inference.py new file mode 100644 index 0000000..46e4e74 --- /dev/null +++ b/inference.py @@ -0,0 +1,154 @@ +import torchaudio +import torch + +from transformers import ( + AutoTokenizer, + AutoModelForCausalLM, +) + +from speechtokenizer import SpeechTokenizer +from WavTokenizer.decoder.pretrained import WavTokenizer +from audiotools import AudioSignal + + +def decode_tts(tokens, quantizer, n_codebooks, n_original_tokens, start_audio_token_id, end_audio_token_id): + # find start and end indices of audio tokens + start = torch.nonzero(tokens == start_audio_token_id) + end = torch.nonzero(tokens == end_audio_token_id) + + start = start[0, -1] + 1 if len(start) else 0 + end = end[0, -1] if len(end) else tokens.shape[-1] + + # subtract length of original vocabulary -> tokens in range [0, 1024) + audio_tokens = tokens[start:end] % n_original_tokens + reminder = audio_tokens.shape[-1] % n_codebooks + + if reminder: + # pad if last frame is incomplete + pad_tokens = torch.zeros(n_codebooks - reminder, device="cuda") + audio_tokens = torch.cat([audio_tokens, pad_tokens], dim=0) + + transposed = audio_tokens.view(-1, n_codebooks).t() + codes = transposed.view(n_codebooks, 1, -1).to(device) + print(codes) + + audio = quantizer.decode(codes).squeeze(0) + + del tokens + del audio_tokens + torch.cuda.empty_cache() + + return AudioSignal(audio.detach().cpu().numpy(), quantizer.sample_rate) + + +def infer_text_to_audio(text, model, tokenizer, quantizer, max_seq_length=1024, top_k=20): + text_tokenized = tokenizer(text, return_tensors="pt") + text_input_tokens = text_tokenized["input_ids"].to(device) + + soa = tokenizer(start_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + eoa = tokenizer(end_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + + text_tokens = torch.cat([text_input_tokens, soa], dim=1) + attention_mask = torch.ones(text_tokens.size(), device=device) + + output_audio_tokens = model.generate( + text_tokens, + attention_mask=attention_mask, + max_new_tokens=max_seq_length, + top_k=top_k, + do_sample=True, + temperature=0.1, + repetition_penalty=1.1, + length_penalty=1.2, + no_repeat_ngram_size=3, + ) + + audio_signal = decode_tts(output_audio_tokens[0], quantizer, 3, len(tokenizer), soa, eoa) + + return audio_signal + + +def infer_audio_to_text(audio_path, model, tokenizer, quantizer_speech, quantizer_wav, max_seq_length=1024, top_k=20): + audio_data, sample_rate = torchaudio.load(audio_path) + + audio = audio_data.view(1, -1).float().to(device) + bandwidth_id = torch.tensor([0]) + + codes_semantics = quantizer_speech.encode(audio.reshape(1, 1, -1)) + raw_semantic_tokens = codes_semantics + len(tokenizer) + raw_semantic_tokens = raw_semantic_tokens[:1].view(1, -1) + + _, codes = quantizer_wav.encode_infer(audio, bandwidth_id=bandwidth_id) + raw_acoustic_tokens = codes + len(tokenizer) + 1024 + raw_acoustic_tokens = raw_acoustic_tokens.view(1, -1) + + audio_tokens = torch.cat([raw_semantic_tokens, raw_acoustic_tokens], dim=1) + + soa = tokenizer(start_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + eoa = tokenizer(end_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device) + audio_tokens = torch.cat([soa, audio_tokens, eoa], dim=1) + tokens = torch.cat([audio_tokens], dim=1) + + attention_mask = torch.ones(tokens.size(), device=device) + + output_text_tokens = model.generate( + tokens, + attention_mask=attention_mask, + max_new_tokens=max_seq_length, + do_sample=True, + temperature=0.1, + top_p=0.9, + top_k=top_k, + ) + + output_text_tokens = output_text_tokens.cpu()[0] + output_text_tokens = output_text_tokens[output_text_tokens < tokenizer(start_audio_token)["input_ids"][-1]] + decoded_text = tokenizer.decode(output_text_tokens, skip_special_tokens=True) + + return decoded_text + + +device = "cuda" + +n_codebooks_tts = 3 +n_codebooks_asr = 1 + +start_audio_token = "<|start_of_audio|>" +end_audio_token = "<|end_of_audio|>" +end_sequence_token = "<|end_of_text|>" + +base_model = "Vikhrmodels/salt-asr_speech_1_wav_1_tts_speech_3_text-10k" + + +if __name__ == "__main__": + tokenizer = AutoTokenizer.from_pretrained(base_model, cache_dir=".") + model = AutoModelForCausalLM.from_pretrained( + base_model, + cache_dir=".", + torch_dtype=torch.bfloat16, + attn_implementation="sdpa", + device_map={"": 0} + ) + + quantizer_speech = SpeechTokenizer.load_from_checkpoint("speechtokenizer/config.json", + "speechtokenizer/SpeechTokenizer.pt") + quantizer_speech = quantizer_speech.eval().to(device) + codebook_size = quantizer_speech.quantizer.bins + + quantizer_wav = WavTokenizer.from_pretrained0802("wavtokenizer/config.yaml", + "wavtokenizer/WavTokenizer_small_600_24k_4096.ckpt") + quantizer_wav = quantizer_wav.to(device) + + text = ("Say 'COUNT NUMBERS FROM ONE TO TEN' with a male speaker delivers a very monotone and " + "low-pitched speech with a moderate speed in a setting with almost no noise, " + "creating a clear and quiet recording.") + + audio_signal = infer_text_to_audio(text, model, tokenizer, quantizer_speech, top_k=60) + audio_signal.write("output.wav") + + audio_path = "./input.wav" + generated_text = infer_audio_to_text(audio_path, model, tokenizer, quantizer_speech, quantizer_wav, top_k=10) + print(generated_text) + + + diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..166bd29 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227754cefd8940d4e35b590d77eedd0ac4f905bb3db6fe1a128b59d6460c3b6a +size 4997319815 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..84cd5a0 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73457999ff16e982d031bc6e06f8909060361c469aa96796f70314505967f7c +size 1459746080 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..e2edb2a --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,262 @@ +{ + "metadata": { + "total_size": 6456975360 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00001-of-00002.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.norm.weight": "pytorch_model-00002-of-00002.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..eb35025 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "additional_special_tokens": [ + { + "content": "<|start_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } + ], + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "[PAD]" +} diff --git a/speechtokenizer/SpeechTokenizer.pt b/speechtokenizer/SpeechTokenizer.pt new file mode 100644 index 0000000..c81992f --- /dev/null +++ b/speechtokenizer/SpeechTokenizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04593b6c9a4b475f91ca481141a6ef5b23e6ac112f347dd2b2717f193c1c728 +size 481906997 diff --git a/speechtokenizer/config.json b/speechtokenizer/config.json new file mode 100644 index 0000000..6a66329 --- /dev/null +++ b/speechtokenizer/config.json @@ -0,0 +1,49 @@ +{ + "resblock": "1", + "num_gpus": 3, + "batch_size": 60, + "learning_rate": 0.0001, + "adam_b1": 0.5, + "adam_b2": 0.9, + "lr_decay": 0.98, + "seed": 1234, + "lambda_distill": 0.15, + + "n_filters": 64, + "strides": [8,5,4,2], + "dimension": 1024, + "semantic_dimension": 768, + "bidirectional": true, + "dilation_base": 2, + "residual_kernel_size": 3, + "n_residual_layers": 1, + "lstm_layers": 2, + "activation": "ELU", + + + "segment_size": 48000, + "num_mels": 80, + "num_freq": 1025, + "n_fft": 1024, + "hop_size": 240, + "win_size": 1024, + + "sampling_rate": 16000, + "sample_rate": 16000, + + "codebook_size": 1024, + "n_q": 8, + + "fmin": 0, + "fmax": 8000, + "fmax_for_loss": null, + + "num_workers": 12, + + "dist_config": { + "dist_backend": "nccl", + "dist_url": "tcp://localhost:54322", + "world_size": 1 + } +} + diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..9fb510d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc582d0849576e5e5308d8710b29a943b6d23a948280ac90523b8acbc64dded9 +size 9086227 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..af9029e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2090 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128256": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128257": { + "content": "<|start_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128258": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|start_of_audio|>", + "<|end_of_audio|>" + ], + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/wavtokenizer/WavTokenizer_small_600_24k_4096.ckpt b/wavtokenizer/WavTokenizer_small_600_24k_4096.ckpt new file mode 100644 index 0000000..1856c59 --- /dev/null +++ b/wavtokenizer/WavTokenizer_small_600_24k_4096.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d44c40fbb83d2d42329ac098e252a31b5708fb7b3bf864d108dd3ed26911d004 +size 1589082492 diff --git a/wavtokenizer/config.yaml b/wavtokenizer/config.yaml new file mode 100644 index 0000000..a42e514 --- /dev/null +++ b/wavtokenizer/config.yaml @@ -0,0 +1,93 @@ +seed_everything: 3407 + +data: + class_path: decoder.dataset.VocosDataModule + init_args: + train_params: + filelist_path: ./WavTokenizer/data/train/libritts_train + sampling_rate: 24000 + num_samples: 72000 + batch_size: 40 # 20 + num_workers: 8 + + val_params: + filelist_path: ./WavTokenizer/data/infer/librttts_val + sampling_rate: 24000 + num_samples: 72000 + batch_size: 5 # 10 + num_workers: 8 + +model: + class_path: decoder.experiment.WavTokenizer + init_args: + sample_rate: 24000 + initial_learning_rate: 2e-4 + mel_loss_coeff: 45 + mrd_loss_coeff: 1.0 + num_warmup_steps: 0 # Optimizers warmup steps + pretrain_mel_steps: 0 # 0 means GAN objective from the first iteration + + # automatic evaluation + evaluate_utmos: true + evaluate_pesq: true + evaluate_periodicty: true + + resume: false + resume_config: ./WavTokenizer/configs/wavtokenizer_smalldata_frame40_3s_nq1_code16384_dim512_kmeans800_attn.yaml + resume_model: ./version_3/checkpoints/xxx.ckpt + + feature_extractor: + class_path: decoder.feature_extractors.EncodecFeatures + init_args: + encodec_model: encodec_24khz + bandwidths: [6.6, 6.6, 6.6, 6.6] + train_codebooks: true + num_quantizers: 1 + dowmsamples: [6, 5, 5, 4] + vq_bins: 4096 + vq_kmeans: 200 + + backbone: + class_path: decoder.models.VocosBackbone + init_args: + input_channels: 512 + dim: 768 + intermediate_dim: 2304 + num_layers: 12 + adanorm_num_embeddings: 4 + + head: + class_path: decoder.heads.ISTFTHead + init_args: + dim: 768 + n_fft: 2400 + hop_length: 600 + padding: same + +trainer: + logger: + class_path: pytorch_lightning.loggers.TensorBoardLogger + init_args: + save_dir: ./WavTokenizer/result/train/wavtokenizer_smalldata_frame40_3s_nq1_code4096_dim512_kmeans200_attn/ + callbacks: + - class_path: pytorch_lightning.callbacks.LearningRateMonitor + - class_path: pytorch_lightning.callbacks.ModelSummary + init_args: + max_depth: 2 + - class_path: pytorch_lightning.callbacks.ModelCheckpoint + init_args: + monitor: val_loss + filename: wavtokenizer_checkpoint_{epoch}_{step}_{val_loss:.4f} + save_top_k: 10 + save_last: true + - class_path: decoder.helpers.GradNormCallback + + # Lightning calculates max_steps across all optimizer steps (rather than number of batches) + # This equals to 1M steps per generator and 1M per discriminator + max_steps: 20000000 + # You might want to limit val batches when evaluating all the metrics, as they are time-consuming + limit_val_batches: 200 + accelerator: gpu + strategy: ddp + devices: [0,1,2,3,4,5,6,7] + log_every_n_steps: 1000