speechbrainteam commited on
Commit
5a0a236
1 Parent(s): 4ceee33

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -34,9 +34,9 @@ The performance of the model is the following:
34
  ## Pipeline description
35
 
36
  This ASR system is composed of 2 different but linked blocks:
37
- 1-Tokenizer (unigram) that transforms words into subword units and trained with
38
  the train transcriptions (train.tsv) of CommonVoice (FR).
39
- 2- Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of
40
  N blocks of convolutional neural networks with normalization and pooling on the
41
  frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain
42
  the final acoustic representation that is given to the CTC and attention decoders.
@@ -78,7 +78,7 @@ The SpeechBrain team does not provide any warranty on the performance achieved b
78
  year = {2021},
79
  publisher = {GitHub},
80
  journal = {GitHub repository},
81
- howpublished = {\url{https://github.com/speechbrain/speechbrain}},
82
  }
83
  ```
84
 
34
  ## Pipeline description
35
 
36
  This ASR system is composed of 2 different but linked blocks:
37
+ 1. Tokenizer (unigram) that transforms words into subword units and trained with
38
  the train transcriptions (train.tsv) of CommonVoice (FR).
39
+ 2. Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of
40
  N blocks of convolutional neural networks with normalization and pooling on the
41
  frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain
42
  the final acoustic representation that is given to the CTC and attention decoders.
78
  year = {2021},
79
  publisher = {GitHub},
80
  journal = {GitHub repository},
81
+ howpublished = {\\url{https://github.com/speechbrain/speechbrain}},
82
  }
83
  ```
84