初始化项目，由ModelHub XC社区提供模型

Model: bond005/wav2vec2-large-ru-golos
Source: Original Platform

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model 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
+*.pt 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
+*.wasm 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

README.md

@@ -0,0 +1,227 @@
+---
+datasets:
+- SberDevices/Golos
+- bond005/sova_rudevices
+- bond005/rulibrispeech
+language: ru
+license: apache-2.0
+metrics:
+- wer
+- cer
+library_name: transformers
+pipeline_tag: automatic-speech-recognition
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+widget:
+- example_title: test sound with Russian speech "нейросети это хорошо"
+  src: https://huggingface.co/bond005/wav2vec2-large-ru-golos/resolve/main/test_sound_ru.flac
+model-index:
+- name: XLSR Wav2Vec2 Russian by Ivan Bondarenko
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Speech Recognition
+    dataset:
+      name: Sberdevices Golos (crowd)
+      type: SberDevices/Golos
+      args: ru
+    metrics:
+    - type: wer
+      value: 10.144
+      name: Test WER
+    - type: cer
+      value: 2.168
+      name: Test CER
+    - type: wer
+      value: 20.353
+      name: Test WER
+    - type: cer
+      value: 6.03
+      name: Test CER
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: Common Voice ru
+      type: common_voice
+      args: ru
+    metrics:
+    - type: wer
+      value: 18.548
+      name: Test WER
+    - type: cer
+      value: 4.0
+      name: Test CER
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: Sova RuDevices
+      type: bond005/sova_rudevices
+      args: ru
+    metrics:
+    - type: wer
+      value: 25.41
+      name: Test WER
+    - type: cer
+      value: 7.965
+      name: Test CER
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: Russian Librispeech
+      type: bond005/rulibrispeech
+      args: ru
+    metrics:
+    - type: wer
+      value: 21.872
+      name: Test WER
+    - type: cer
+      value: 4.469
+      name: Test CER
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: Voxforge Ru
+      type: dangrebenkin/voxforge-ru-dataset
+      args: ru
+    metrics:
+    - type: wer
+      value: 27.084
+      name: Test WER
+    - type: cer
+      value: 6.986
+      name: Test CER
+---
+
+# Wav2Vec2-Large-Ru-Golos
+
+This model is a component of the **Pisets** speech-to-text system, presented in the paper [Pisets: A Robust Speech Recognition System for Lectures and Interviews](https://huggingface.co/papers/2601.18415).
+
+The source code for the **Pisets** system is available on GitHub: [bond005/pisets](https://github.com/bond005/pisets).
+
+The Wav2Vec2 model is based on [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53), fine-tuned in Russian using [Sberdevices Golos](https://huggingface.co/datasets/SberDevices/Golos) with audio augmentations like as pitch shift, acceleration/deceleration of sound, reverberation etc.
+
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+## 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("bond005/wav2vec2-large-ru-golos")
+model = Wav2Vec2ForCTC.from_pretrained("bond005/wav2vec2-large-ru-golos")
+     
+# load the test part of Golos dataset and read first soundfile
+ds = load_dataset("bond005/sberdevices_golos_10h_crowd", split="test")
+ 
+# tokenize
+processed = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest")  # Batch size 1
+ 
+# retrieve logits
+logits = model(processed.input_values, attention_mask=processed.attention_mask).logits
+ 
+# take argmax and decode
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)[0]
+print(transcription)
+```
+
+ ## Evaluation
+ 
+This code snippet shows how to evaluate **bond005/wav2vec2-large-ru-golos** on Golos dataset's "crowd" and "farfield" test data.
+ 
+```python
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import torch
+from jiwer import wer, cer  # we need word error rate (WER) and character error rate (CER)
+
+# load the test part of Golos Crowd and remove samples with empty "true" transcriptions
+golos_crowd_test = load_dataset("bond005/sberdevices_golos_10h_crowd", split="test")
+golos_crowd_test = golos_crowd_test.filter(
+    lambda it1: (it1["transcription"] is not None) and (len(it1["transcription"].strip()) > 0)
+)
+
+# load the test part of Golos Farfield and remove sampels with empty "true" transcriptions
+golos_farfield_test = load_dataset("bond005/sberdevices_golos_100h_farfield", split="test")
+golos_farfield_test = golos_farfield_test.filter(
+    lambda it2: (it2["transcription"] is not None) and (len(it2["transcription"].strip()) > 0)
+)
+
+# load model and tokenizer
+model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
+processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
+
+# recognize one sound
+def map_to_pred(batch):
+    # tokenize and vectorize
+    processed = processor(
+        batch["audio"]["array"], sampling_rate=batch["audio"]["sampling_rate"],
+        return_tensors="pt", padding="longest"
+    )
+    input_values = processed.input_values.to("cuda")
+    attention_mask = processed.attention_mask.to("cuda")
+
+    # recognize
+    with torch.no_grad():
+        logits = model(input_values, attention_mask=attention_mask).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+
+    # decode
+    transcription = processor.batch_decode(predicted_ids)
+    batch["text"] = transcription[0]
+    return batch
+
+# calculate WER and CER on the crowd domain
+crowd_result = golos_crowd_test.map(map_to_pred, remove_columns=["audio"])
+crowd_wer = wer(crowd_result["transcription"], crowd_result["text"])
+crowd_cer = cer(crowd_result["transcription"], crowd_result["text"])
+print("Word error rate on the Crowd domain:", crowd_wer)
+print("Character error rate on the Crowd domain:", crowd_cer)
+
+# calculate WER and CER on the farfield domain
+farfield_result = golos_farfield_test.map(map_to_pred, remove_columns=["audio"])
+farfield_wer = wer(farfield_result["transcription"], farfield_result["text"])
+farfield_cer = cer(farfield_result["transcription"], farfield_result["text"])
+print("Word error rate on the Farfield domain:", farfield_wer)
+print("Character error rate on the Farfield domain:", farfield_cer)
+```
+
+*Result (WER, %)*:
+
+| "crowd" | "farfield" |
+|---------|------------|
+|  10.144 |     20.353 |
+
+*Result (CER, %)*:
+
+| "crowd" | "farfield" |
+|---------|------------|
+|   2.168 |      6.030 |
+
+You can see the evaluation script on other datasets, including Russian Librispeech and SOVA RuDevices, on my Kaggle web-page https://www.kaggle.com/code/bond005/wav2vec2-ru-eval
+
+## Citation
+If you want to cite this model you can use this:
+
+```bibtex
+@misc{bondarenko2022wav2vec2-large-ru-golos,
+  title={XLSR Wav2Vec2 Russian by Ivan Bondarenko},
+  author={Bondarenko, Ivan},
+  publisher={Hugging Face},
+  journal={Hugging Face Hub},
+  howpublished={\url{https://huggingface.co/bond005/wav2vec2-large-ru-golos}},
+  year={2022}
+}
+```

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "/storage0/bi/models/wav2vec2-large-ru-golos",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 37,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2a4ee1d1cb6d5b72c1128c0baaf5ab9c95b4931031604b2d5c9787ebc2781d
+size 1262053549

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "а": 5, "б": 6, "в": 7, "г": 8, "д": 9, "е": 10, "ж": 11, "з": 12, "и": 13, "й": 14, "к": 15, "л": 16, "м": 17, "н": 18, "о": 19, "п": 20, "р": 21, "с": 22, "т": 23, "у": 24, "ф": 25, "х": 26, "ц": 27, "ч": 28, "ш": 29, "щ": 30, "ъ": 31, "ы": 32, "ь": 33, "э": 34, "ю": 35, "я": 36}