patrickvonplaten commited on
Commit
8d88236
1 Parent(s): 0b362f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -83
README.md CHANGED
@@ -1,96 +1,60 @@
1
- # Wav2Vec2 Acoustic Model fine-tuned on LibriSpeech
 
 
 
 
 
2
 
3
- Original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
 
4
 
5
- Paper: https://arxiv.org/abs/2006.11477
6
 
7
- ## Usage
8
 
9
- Make sure you are working on [this branch](https://github.com/huggingface/transformers/tree/add_wav2vec) (which will be merged to master soon hopefully) of transformers:
10
 
11
- ```bash
12
- $ git checkout add_wav2vec
13
- ```
14
 
15
- In the following, we'll show a simple example of how the model can be used for automatic speech recognition.
16
 
17
- First, let's load the model
 
18
 
19
- ```python
20
- from transformers import AutoModelForMaskedLM
21
 
22
- model = AutoModelForMaskedLM.from_pretrained("patrickvonplaten/wav2vec2-base-960h")
23
 
24
- ```
25
 
26
- Next, let's load a dummy librispeech dataset
27
 
28
  ```python
29
- from datasets import load_dataset
30
- import soundfile as sf
31
-
32
- libri_speech_dummy = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
33
-
34
- def map_to_array(batch):
35
- speech_array, _ = sf.read(batch["file"])
36
- batch["speech"] = speech_array
37
- return batch
38
-
39
- libri_speech_dummy = libri_speech_dummy.map(map_to_array, remove_columns=["file"])
40
-
41
- # check out dataset
42
- print(libri_speech_dummy)
43
-
44
- input_speech_16kHz = libri_speech_dummy[2]["speech"]
45
- expected_trans = libri_speech_dummy[2]["text"]
46
- ```
47
-
48
- Cool, now we can run an inference pass to retrieve the logits:
49
-
50
- ```python
51
- import torch
52
- logits = model(torch.tensor(input_speech_16kHz)[None, :])
53
-
54
- # use highest probability logits
55
- pred_ids = torch.argmax(logits[0], axis=-1)
56
- ```
57
-
58
- Finally, let's decode the prediction.
59
- Let's create a simple CTC-Decoder:
60
-
61
- ```python
62
- import numpy as np
63
- from itertools import groupby
64
-
65
- class Decoder:
66
- def __init__(self, json_dict):
67
- self.dict = json_dict
68
- self.look_up = np.asarray(list(self.dict.keys()))
69
-
70
- def decode(self, ids):
71
- converted_tokens = self.look_up[ids]
72
- fused_tokens = [tok[0] for tok in groupby(converted_tokens)]
73
- output = ' '.join(''.join(''.join(fused_tokens).split("<s>")).split("|"))
74
- return output
75
- ```
76
-
77
- and instantiate with the corresponding dict.
78
-
79
- ```python
80
- # hard-coded json dict taken from: https://dl.fbaipublicfiles.com/fairseq/wav2vec/dict.ltr.txt
81
- json_dict = {"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 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}
82
-
83
- decoder = Decoder(json_dict=json_dict)
84
- ```
85
-
86
- and decode the result
87
-
88
- ```python
89
- pred_trans = decoder.decode(pred_ids)
90
-
91
- print("Prediction:\n", pred_trans)
92
- print("\n" + 50 * "=" + "\n")
93
- print("Correct result:\n", expected_trans)
94
- ```
95
-
96
- 🎉
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - librispeech_asr
5
+ tags:
6
+ - speech
7
 
8
+ license: apache-2.0
9
+ ---
10
 
11
+ # Wav2Vec2-Base-960h
12
 
13
+ [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
14
 
15
+ The base model pretrained and fine-tuned on 960 hours of Librispeech.
16
 
17
+ [Paper](https://arxiv.org/abs/2006.11477)
 
 
18
 
19
+ Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli
20
 
21
+ **Abstract**
22
+ 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.
23
 
24
+ The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
 
25
 
 
26
 
27
+ # Usage
28
 
29
+ The model can be used as follows to classify some speech input
30
 
31
  ```python
32
+ from transformers import Wav2Vec2Tokenizer, Wav2Vec2Model
33
+ from datasets import load_dataset
34
+ import soundfile as sf
35
+ import torch
36
+
37
+ # load model and tokenizer
38
+ tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
39
+ model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-base-960h")
40
+
41
+ # define function to read in sound file
42
+ def map_to_array(batch):
43
+ speech, _ = sf.read(batch["file"])
44
+ batch["speech"] = speech
45
+ return batch
46
+
47
+ # load dummy dataset and read soundfiles
48
+ ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
49
+ ds = ds.map(map_to_array)
50
+
51
+ # tokenize
52
+ input_values = tokenizer(ds["speech"][:2], return_tensors="pt", padding="longest").input_values # Batch size 1
53
+
54
+ # retrieve logits
55
+ logits = model(input_values).logits
56
+
57
+ # take argmax and decode
58
+ predicted_ids = torch.argmax(logits, dim=-1)
59
+ transcription = tokenizer.batch_decode(predicted_ids)
60
+ ```