初始化项目，由ModelHub XC社区提供模型

Model: aadel4/omniASR-CTC-1B-v2
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+tags:
+- speech
+- audio
+- wav2vec2
+- automatic-speech-recognition
+pipeline_tag: automatic-speech-recognition
+---
+
+# omniASR-CTC-1B-v2
+
+Wav2Vec2 CTC ASR model (v2) converted from the [OmniLingual](https://github.com/facebookresearch/omnilingual-asr) fairseq2 checkpoint `omniASR_CTC_1B_v2`.
+
+This model outputs CTC logits over a SentencePiece vocabulary and can transcribe speech in multiple languages.
+
+# Code Base
+
+The code base for the conversion can be found [here](https://github.com/ahmedadelattia/omnilingual_to_hf). I was only able to convert the 300M and 1B models due to GPU limitations. Contributions are welcome.
+
+## Model details
+
+| Property             | Value |
+|---|---|
+| HF class             | `Wav2Vec2ForCTC` |
+| Encoder layers       | 48 |
+| Hidden size          | 1280 |
+| Attention heads      | 16 |
+| FFN intermediate     | 5120 |
+| Vocabulary size      | 10288 |
+| Source framework     | fairseq2 |
+| Source card          | `omniASR_CTC_1B_v2` |
+| Parity verification  | ✅ Verified |
+
+
+Numerical parity against the original fairseq2 checkpoint has been confirmed: outputs match to within `atol=1e-4` on a held-out audio sample.
+
+Sample transcriptions on the held-out audio clip:
+
+| Model | Transcript |
+|---|---|
+| fairseq2 (source) | `concord returned to its place amidst the tents` |
+| HuggingFace (this repo) | `concord returned to its place amidst the tents` |
+
+## Usage
+
+```python
+from transformers import Wav2Vec2ForCTC, AutoProcessor
+import torch, torchaudio
+
+processor = AutoProcessor.from_pretrained("aadel4/omniASR-CTC-1B-v2")
+model     = Wav2Vec2ForCTC.from_pretrained("aadel4/omniASR-CTC-1B-v2")
+model.eval()
+
+waveform, sr = torchaudio.load("audio.wav")
+if sr != 16_000:
+    waveform = torchaudio.functional.resample(waveform, sr, 16_000)
+
+inputs = processor(
+    waveform.squeeze().numpy(), sampling_rate=16_000, return_tensors="pt"
+)
+with torch.no_grad():
+    logits = model(**inputs).logits          # (1, T, vocab)
+
+pred_ids   = torch.argmax(logits, dim=-1)
+transcript = processor.decode(pred_ids[0])
+print(transcript)
+```

config.json

@@ -0,0 +1,106 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "5.3.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 10288,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157d809f748c1414bcbed7fb0eeb09dd4b04f11994298d1c99b08c6a975f40f0
+size 3902806784

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "sampling_rate": 16000,
+  "padding_value": 0.0,
+  "do_normalize": true,
+  "return_attention_mask": false
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<s>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<s>",
+  "word_delimiter_token": " ",
+  "do_lower_case": false,
+  "replace_word_delimiter_char": " "
+}