初始化项目，由ModelHub XC社区提供模型

Model: facebook/wav2vec2-base-10k-voxpopuli-ft-en
Source: Original Platform

.gitattributes

@@ -0,0 +1,17 @@
+*.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

README.md

@@ -0,0 +1,69 @@
+---
+language: en
+tags:
+- audio
+- automatic-speech-recognition
+- voxpopuli
+license: cc-by-nc-4.0
+---
+
+# Wav2Vec2-Base-VoxPopuli-Finetuned
+
+[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) base model pretrained on the 10K unlabeled subset of [VoxPopuli corpus](https://arxiv.org/abs/2101.00390) and fine-tuned on the transcribed data in en (refer to Table 1 of paper for more information).
+
+**Paper**: *[VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation
+Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/2101.00390)*
+
+**Authors**: *Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux* from *Facebook AI*
+
+See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/)
+
+
+# Usage for inference
+
+In the following it is shown how the model can be used in inference on a sample of the [Common Voice dataset](https://commonvoice.mozilla.org/en/datasets)
+
+```python
+#!/usr/bin/env python3
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+from datasets import load_dataset
+import torchaudio
+import torch
+
+# resample audio
+
+# load model & processor
+model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-10k-voxpopuli-ft-en")
+processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-10k-voxpopuli-ft-en")
+
+# load dataset
+ds = load_dataset("common_voice", "en", split="validation[:1%]")
+
+# common voice does not match target sampling rate
+common_voice_sample_rate = 48000
+target_sample_rate = 16000
+
+resampler = torchaudio.transforms.Resample(common_voice_sample_rate, target_sample_rate)
+
+
+# define mapping fn to read in sound file and resample
+def map_to_array(batch):
+    speech, _ = torchaudio.load(batch["path"])
+    speech = resampler(speech)
+    batch["speech"] = speech[0]
+    return batch
+
+
+# load all audio files
+ds = ds.map(map_to_array)
+
+# run inference on the first 5 data samples
+inputs = processor(ds[:5]["speech"], sampling_rate=target_sample_rate, return_tensors="pt", padding=True)
+
+# inference
+logits = model(**inputs).logits
+predicted_ids = torch.argmax(logits, axis=-1)
+
+print(processor.batch_decode(predicted_ids))
+```
+

config.json

@@ -0,0 +1,68 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "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,
+  "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,
+  "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_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "transformers_version": "4.6.0.dev0",
+  "vocab_size": 32
+}

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": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1334f627b73604c14d3f79c2007c42f3b46b2d66ecb81f35c57f522f6e28d485
+size 377672556

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 @@
+{"<s>": 1, "<pad>": 0, "</s>": 2, "<unk>": 3, "|": 4, "e": 5, "t": 6, "o": 7, "i": 8, "a": 9, "n": 10, "s": 11, "r": 12, "h": 13, "l": 14, "d": 15, "c": 16, "u": 17, "m": 18, "p": 19, "f": 20, "g": 21, "w": 22, "y": 23, "b": 24, "v": 25, "k": 26, "x": 27, "j": 28, "q": 29, "z": 30, "1": 31}