add init finetune vi model

README.md

@@ -0,0 +1,112 @@
+---
+language: en
+datasets:
+- librispeech_asr
+tags:
+- audio
+- automatic-speech-recognition
+license: apache-2.0
+widget:
+- label: Librispeech sample 1
+  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
+- label: Librispeech sample 2
+  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
+---
+
+# 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 soundfile as sf
+ import torch
+ 
+ # load model and tokenizer
+ processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
+ model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
+ 
+ # define function to read in sound file
+ def map_to_array(batch):
+     speech, _ = sf.read(batch["file"])
+     batch["speech"] = speech
+     return batch
+     
+ # load dummy dataset and read soundfiles
+ ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
+ ds = ds.map(map_to_array)
+ 
+ # tokenize
+ input_values = processor(ds["speech"][:2], 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 soundfile as sf
+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_array(batch):
+    speech, _ = sf.read(batch["file"])
+    batch["speech"] = speech
+    return batch
+
+librispeech_eval = librispeech_eval.map(map_to_array)
+
+def map_to_pred(batch):
+    input_values = processor(batch["speech"], 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=["speech"])
+
+print("WER:", wer(result["text"], result["transcription"]))
+```
+
+*Result (WER)*:
+
+| "clean" | "other" |
+|---|---|
+| 3.4 | 8.6 |

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "/content/vaw2tmp/model-bin/finetune/base/checkpoint-146596",
+  "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": "mean",
+  "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": true,
+  "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": 109,
+  "proj_codevector_dim": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "vocab_size": 110
+}

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2529ffc057c90b3d576ea109999ea49f3bab9691f7a93297a91d69ce8c981f84
+size 377906903

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"ẻ": 0, "6": 1, "ụ": 2, "í": 3, "3": 4, "ỹ": 5, "ý": 6, "ẩ": 7, "ở": 8, "ề": 9, "õ": 10, "7": 11, "ê": 12, "ứ": 13, "ỏ": 14, "v": 15, "ỷ": 16, "a": 17, "l": 18, "ự": 19, "q": 20, "ờ": 21, "j": 22, "ố": 23, "à": 24, "ỗ": 25, "n": 26, "é": 27, "ủ": 28, "у": 29, "ô": 30, "u": 31, "y": 32, "ằ": 33, "4": 34, "w": 35, "b": 36, "ệ": 37, "ễ": 38, "s": 39, "ì": 40, "ầ": 41, "ỵ": 42, "8": 43, "d": 44, "ể": 45, "r": 47, "ũ": 48, "c": 49, "ạ": 50, "9": 51, "ế": 52, "ù": 53, "ỡ": 54, "2": 55, "t": 56, "i": 57, "g": 58, "́": 59, "ử": 60, "̀": 61, "á": 62, "0": 63, "ậ": 64, "e": 65, "ộ": 66, "m": 67, "ẳ": 68, "ợ": 69, "ĩ": 70, "h": 71, "â": 72, "ú": 73, "ọ": 74, "ồ": 75, "ặ": 76, "f": 77, "ữ": 78, "ắ": 79, "ỳ": 80, "x": 81, "ó": 82, "ã": 83, "ổ": 84, "ị": 85, "̣": 86, "z": 87, "ả": 88, "đ": 89, "è": 90, "ừ": 91, "ò": 92, "ẵ": 93, "1": 94, "ơ": 95, "k": 96, "ẫ": 97, "p": 98, "ấ": 99, "ẽ": 100, "ỉ": 101, "ớ": 102, "ẹ": 103, "ă": 104, "o": 105, "ư": 106, "5": 107, "|": 46, "<unk>": 108, "<pad>": 109}