Titouan commited on
Commit
e1bcce3
1 Parent(s): b38bb46

model card

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: "en"
3
+ thumbnail:
4
+ tags:
5
+ - ASR
6
+ - CTC
7
+ - Attention
8
+ - Tranformer
9
+ - pytorch
10
+ license: "apache-2.0"
11
+ datasets:
12
+ - librispeech
13
+ metrics:
14
+ - wer
15
+ - cer
16
+ ---
17
+
18
+ # CRDNN with CTC/Attention and RNNLM trained on LibriSpeech
19
+
20
+ This repository provides all the necessary tools to perform automatic speech
21
+ recognition from an end-to-end system pretrained on LibriSpeech (EN) within
22
+ SpeechBrain. For a better experience we encourage you to learn more about
23
+ [SpeechBrain](https://speechbrain.github.io). The given ASR model performance are:
24
+
25
+ | Release | Test clean WER | Test other WER | GPUs |
26
+ |:-------------:|:--------------:|:--------------:|:--------:|
27
+ | 05-03-21 | 2.90 | 8.51 | 1xV100 16GB |
28
+
29
+ ## Pipeline description
30
+
31
+ This ASR system is composed with 3 different but linked blocks:
32
+ 1. Tokenizer (unigram) that transforms words into subword units and trained with
33
+ the train transcriptions of LibriSpeech.
34
+ 2. Neural language model (Transformer LM) trained on the full 10M words dataset.
35
+ 3. Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of
36
+ N blocks of convolutional neural networks with normalisation and pooling on the
37
+ frequency domain. Then, a bidirectional LSTM with projection layers is connected
38
+ to a final DNN to obtain the final acoustic representation that is given to
39
+ the CTC and attention decoders.
40
+
41
+ ## Intended uses & limitations
42
+
43
+ This model has been primilarly developed to be run within SpeechBrain as a pretrained ASR model
44
+ for the english language. Thanks to the flexibility of SpeechBrain, any of the 3 blocks
45
+ detailed above can be extracted and connected to you custom pipeline as long as SpeechBrain is
46
+ installed.
47
+
48
+ ## Install SpeechBrain
49
+
50
+ First of all, please install SpeechBrain with the following command:
51
+
52
+ ```
53
+ pip install \\we hide ! SpeechBrain is still private :p
54
+ ```
55
+
56
+ Please notice that we encourage you to read our tutorials and learn more about
57
+ [SpeechBrain](https://speechbrain.github.io).
58
+
59
+ ### Transcribing your own audio files
60
+
61
+ ```python
62
+ from speechbrain.pretrained import EncoderDecoderASR
63
+
64
+ asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-transformerlm-librispeech")
65
+ asr_model.transcribe_file("path_to_your_file.wav")
66
+
67
+ ```
68
+
69
+ #### Referencing SpeechBrain
70
+
71
+ ```
72
+ @misc{SB2021,
73
+ author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
74
+ title = {SpeechBrain},
75
+ year = {2021},
76
+ publisher = {GitHub},
77
+ journal = {GitHub repository},
78
+ howpublished = {\url{https://github.com/speechbrain/speechbrain}},
79
+ }
80
+ ```