patrickvonplaten commited on
Commit
eab3722
1 Parent(s): 8f79ee3

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - librispeech_asr
5
+ tags:
6
+ - speech
7
+
8
+ license: apache-2.0
9
+ ---
10
+
11
+ # Wav2Vec2-Large-960h-Lv60 + Self-Training
12
+
13
+ [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
14
+
15
+ The large model pretrained and fine-tuned on 960 hours of Libri-Light and Librispeech. Model was trained with [Self-Training objective](https://arxiv.org/abs/2010.11430)
16
+
17
+ [Paper](https://arxiv.org/abs/2006.11477)
18
+
19
+ Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli
20
+
21
+ **Abstract**
22
+
23
+ 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.
24
+
25
+ The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
26
+
27
+
28
+ # Usage
29
+
30
+ To transcribe audio files the model can be used as a standalone acoustic model as follows:
31
+
32
+ ```python
33
+ from transformers import Wav2Vec2Tokenizer, Wav2Vec2Model
34
+ from datasets import load_dataset
35
+ import soundfile as sf
36
+ import torch
37
+
38
+ # load model and tokenizer
39
+ tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
40
+ model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
41
+
42
+ # define function to read in sound file
43
+ def map_to_array(batch):
44
+ speech, _ = sf.read(batch["file"])
45
+ batch["speech"] = speech
46
+ return batch
47
+
48
+ # load dummy dataset and read soundfiles
49
+ ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
50
+ ds = ds.map(map_to_array)
51
+
52
+ # tokenize
53
+ input_values = tokenizer(ds["speech"][:2], return_tensors="pt", padding="longest").input_values # Batch size 1
54
+
55
+ # retrieve logits
56
+ logits = model(input_values).logits
57
+
58
+ # take argmax and decode
59
+ predicted_ids = torch.argmax(logits, dim=-1)
60
+ transcription = tokenizer.batch_decode(predicted_ids)
61
+ ```