commit cc5d2e212e3afe7f553809df88188bba2fc6bf83 Author: ModelHub XC Date: Wed May 13 08:52:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: KBLab/wav2vec2-large-voxrex-swedish Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d1395b --- /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 +*tfevents* 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..002762c --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +language: sv +arxiv: https://arxiv.org/abs/2205.03026 +datasets: +- common_voice +- NST_Swedish_ASR_Database +- P4 +metrics: +- wer +tags: +- audio +- automatic-speech-recognition +- speech +- hf-asr-leaderboard +license: cc0-1.0 +model-index: +- name: Wav2vec 2.0 large VoxRex Swedish + results: + - task: + name: Speech Recognition + type: automatic-speech-recognition + dataset: + name: Common Voice + type: common_voice + args: sv-SE + metrics: + - name: Test WER + type: wer + value: 8.49 +--- +# Wav2vec 2.0 large VoxRex Swedish (C) + +Finetuned version of KBs [VoxRex large](https://huggingface.co/KBLab/wav2vec2-large-voxrex) model using Swedish radio broadcasts, NST and Common Voice data. Evalutation without a language model gives the following: WER for NST + Common Voice test set (2% of total sentences) is **2.5%**. WER for Common Voice test set is **8.49%** directly and **7.37%** with a 4-gram language model. + +When using this model, make sure that your speech input is sampled at 16kHz. + +**Update 2022-01-10:** Updated to VoxRex-C version. + +**Update 2022-05-16:** Paper is is [here](https://arxiv.org/abs/2205.03026). + +# Performance\* + +![Comparison](comparison.png "Comparison") +
*Chart shows performance without the additional 20k steps of Common Voice fine-tuning
+ +## Training +This model has been fine-tuned for 120000 updates on NST + CommonVoice and then for an additional 20000 updates on CommonVoice only. The additional fine-tuning on CommonVoice hurts performance on the NST+CommonVoice test set somewhat and, unsurprisingly, improves it on the CommonVoice test set. It seems to perform generally better though [citation needed]. + +![WER during training](chart_1.svg "WER") + +## Usage +The model can be used directly (without a language model) as follows: +```python +import torch +import torchaudio +from datasets import load_dataset +from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor +test_dataset = load_dataset("common_voice", "sv-SE", split="test[:2%]"). +processor = Wav2Vec2Processor.from_pretrained("KBLab/wav2vec2-large-voxrex-swedish") +model = Wav2Vec2ForCTC.from_pretrained("KBLab/wav2vec2-large-voxrex-swedish") +resampler = torchaudio.transforms.Resample(48_000, 16_000) +# Preprocessing the datasets. +# We need to read the aduio files as arrays +def speech_file_to_array_fn(batch): + speech_array, sampling_rate = torchaudio.load(batch["path"]) + batch["speech"] = resampler(speech_array).squeeze().numpy() + return batch +test_dataset = test_dataset.map(speech_file_to_array_fn) +inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True) +with torch.no_grad(): + logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits +predicted_ids = torch.argmax(logits, dim=-1) +print("Prediction:", processor.batch_decode(predicted_ids)) +print("Reference:", test_dataset["sentence"][:2]) +``` + +## Citation + +https://arxiv.org/abs/2205.03026 + +``` +@inproceedings{malmsten2022hearing, + title={Hearing voices at the national library : a speech corpus and acoustic model for the Swedish language}, + author={Malmsten, Martin and Haffenden, Chris and B{\"o}rjeson, Love}, + booktitle={Proceeding of Fonetik 2022 : Speech, Music and Hearing Quarterly Progress and Status Report, TMH-QPSR}, + volume={3}, + year={2022} +} +``` \ No newline at end of file diff --git a/chart_1.svg b/chart_1.svg new file mode 100644 index 0000000..00737aa --- /dev/null +++ b/chart_1.svg @@ -0,0 +1 @@ + \ No newline at end of file diff --git a/comparison.png b/comparison.png new file mode 100644 index 0000000..bdcedeb Binary files /dev/null and b/comparison.png differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..d561203 --- /dev/null +++ b/config.json @@ -0,0 +1,83 @@ +{ + "activation_dropout": 0.05, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2ForCTC" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "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": true, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": true, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "layer", + "feat_proj_dropout": 0.05, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.0, + "gradient_checkpointing": true, + "hidden_act": "gelu", + "hidden_dropout": 0.05, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "layerdrop": 0.05, + "mask_channel_length": 10, + "mask_channel_min_space": 1, + "mask_channel_other": 0.0, + "mask_channel_prob": 0.0, + "mask_channel_selection": "static", + "mask_feature_length": 10, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_space": 1, + "mask_time_other": 0.0, + "mask_time_prob": 0.05, + "mask_time_selection": "static", + "model_type": "wav2vec2", + "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": 24, + "num_negatives": 100, + "pad_token_id": 0, + "proj_codevector_dim": 256, + "transformers_version": "4.8.2", + "vocab_size": 46 +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..3001d99 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09f24c48fdb07865246e3cf06fc47c881ce911f02a6983bce70595ba417e02b +size 1261996032 diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..36ebe8b --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,9 @@ +{ + "do_normalize": true, + "feature_extractor_type": "Wav2Vec2FeatureExtractor", + "feature_size": 1, + "padding_side": "right", + "padding_value": 0, + "return_attention_mask": true, + "sampling_rate": 16000 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..9a933b4 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7138b3f9c5700388ddbd8b08a194290529778aba95327e7445a621cbe24ef508 +size 1262106353 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/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..92169da --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,9 @@ +{ + "bos_token" : "", + "do_lower_case" : true, + "eos_token" : "", + "pad_token" : "", + "tokenizer_class" : "Wav2Vec2CTCTokenizer", + "unk_token" : "", + "word_delimiter_token" : "|" +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c477f4 --- /dev/null +++ b/vocab.json @@ -0,0 +1 @@ +{"": 0, "": 1, "": 2, "": 3, "|": 4, "T": 5, "E": 6, "A": 7, "N": 8, "R": 9, "S": 10, "I": 11, "L": 12, "D": 13, "O": 14, "M": 15, "K": 16, "G": 17, "U": 18, "V": 19, "F": 20, "H": 21, "Ä": 22, "Å": 23, "P": 24, "Ö": 25, "B": 26, "J": 27, "C": 28, "Y": 29, "X": 30, "W": 31, "Z": 32, "É": 33, "Q": 34, "8": 35, "2": 36, "5": 37, "9": 38, "1": 39, "6": 40, "7": 41, "3": 42, "4": 43, "0": 44, "'": 45} \ No newline at end of file