commit cc3f7872a7004637f2420e90b5d15ef916352b16 Author: ModelHub XC Date: Sun Nov 1 00:00:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: facebook/wav2vec2-base-960h Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf6d51f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,18 @@ +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tar.gz filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c7fe204 --- /dev/null +++ b/README.md @@ -0,0 +1,128 @@ +--- +language: en +datasets: +- librispeech_asr +tags: +- audio +- automatic-speech-recognition +- hf-asr-leaderboard +license: apache-2.0 +widget: +- example_title: Librispeech sample 1 + src: https://cdn-media.huggingface.co/speech_samples/sample1.flac +- example_title: Librispeech sample 2 + src: https://cdn-media.huggingface.co/speech_samples/sample2.flac +model-index: +- name: wav2vec2-base-960h + results: + - task: + name: Automatic Speech Recognition + type: automatic-speech-recognition + dataset: + name: LibriSpeech (clean) + type: librispeech_asr + config: clean + split: test + args: + language: en + metrics: + - name: Test WER + type: wer + value: 3.4 + - task: + name: Automatic Speech Recognition + type: automatic-speech-recognition + dataset: + name: LibriSpeech (other) + type: librispeech_asr + config: other + split: test + args: + language: en + metrics: + - name: Test WER + type: wer + value: 8.6 +--- + +# Wav2Vec2-Base-960h + +[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) + +The base model pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model +make sure that your speech input is also sampled at 16Khz. + +[Paper](https://arxiv.org/abs/2006.11477) + +Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli + +**Abstract** + +We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. + +The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20. + + +# Usage + +To transcribe audio files the model can be used as a standalone acoustic model as follows: + +```python + from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC + from datasets import load_dataset + import torch + + # load model and tokenizer + processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h") + model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h") + + # load dummy dataset and read soundfiles + ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation") + + # tokenize + input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values # Batch size 1 + + # retrieve logits + logits = model(input_values).logits + + # take argmax and decode + predicted_ids = torch.argmax(logits, dim=-1) + transcription = processor.batch_decode(predicted_ids) + ``` + + ## Evaluation + + This code snippet shows how to evaluate **facebook/wav2vec2-base-960h** on LibriSpeech's "clean" and "other" test data. + +```python +from datasets import load_dataset +from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor +import torch +from jiwer import wer + + +librispeech_eval = load_dataset("librispeech_asr", "clean", split="test") + +model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda") +processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h") + +def map_to_pred(batch): + input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values + with torch.no_grad(): + logits = model(input_values.to("cuda")).logits + + predicted_ids = torch.argmax(logits, dim=-1) + transcription = processor.batch_decode(predicted_ids) + batch["transcription"] = transcription + return batch + +result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["audio"]) + +print("WER:", wer(result["text"], result["transcription"])) +``` + +*Result (WER)*: + +| "clean" | "other" | +|---|---| +| 3.4 | 8.6 | \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8ca9cc7 --- /dev/null +++ b/config.json @@ -0,0 +1,77 @@ +{ + "_name_or_path": "facebook/wav2vec2-base-960h", + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2ForCTC" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "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": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.1, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_prob": 0.05, + "model_type": "wav2vec2", + "num_attention_heads": 12, + "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": 12, + "num_negatives": 100, + "pad_token_id": 0, + "proj_codevector_dim": 256, + "transformers_version": "4.7.0.dev0", + "vocab_size": 32 +} diff --git a/feature_extractor_config.json b/feature_extractor_config.json new file mode 100644 index 0000000..52fdd74 --- /dev/null +++ b/feature_extractor_config.json @@ -0,0 +1,8 @@ +{ + "do_normalize": true, + "feature_dim": 1, + "padding_side": "right", + "padding_value": 0.0, + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..9425626 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa76ab2243c81747a1f832954586bc566090c83a0ac167df6f31f0fa917d74a +size 377607901 diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..3f24dc0 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,8 @@ +{ + "do_normalize": true, + "feature_size": 1, + "padding_side": "right", + "padding_value": 0.0, + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..d630db4 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34f9827b034a1b9141dbf6f652f8a60eda61cdf5771c9e05bfa99033c92cd96 +size 377667514 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..25bc396 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "unk_token": "", "pad_token": ""} \ No newline at end of file diff --git a/tf_model.h5 b/tf_model.h5 new file mode 100644 index 0000000..e6d1d69 --- /dev/null +++ b/tf_model.h5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412742825972a6e2e877255ccd8b3416e618df15a7f1e5e4f736aa3632ce33b5 +size 377840624 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..978a15a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"unk_token": "", "bos_token": "", "eos_token": "", "pad_token": "", "do_lower_case": false, "return_attention_mask": false, "do_normalize": true} \ No newline at end of file diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..88181b9 --- /dev/null +++ b/vocab.json @@ -0,0 +1 @@ +{"": 0, "": 1, "": 2, "": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31} \ No newline at end of file