poonehmousavi commited on
Commit
2df2b7b
1 Parent(s): 7ae828f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  language:
3
- - fr
4
  thumbnail: null
5
  tags:
6
  - automatic-speech-recognition
@@ -14,13 +14,13 @@ datasets:
14
  metrics:
15
  - name: Test WER
16
  type: wer
17
- value: ' 17.58'
18
  ---
19
 
20
  <iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
21
  <br/><br/>
22
 
23
- # Transducer trained on CommonVoice 14.0 French (No LM)
24
  This repository provides all the necessary tools to perform automatic speech
25
  recognition from an end-to-end system within
26
  SpeechBrain. For a better experience, we encourage you to learn more about
@@ -29,7 +29,7 @@ The performance of the model is the following:
29
 
30
  | Release | Test CER | Test WER | GPUs |
31
  |:-------------:|:--------------:|:--------------:| :--------:|
32
- | 15.08.23 | 7.61 | 17.58 | 1xV100 32GB |
33
 
34
  ## Credits
35
  The model is provided by [vitas.ai](https://www.vitas.ai/).
@@ -54,12 +54,12 @@ pip install speechbrain
54
  Please notice that we encourage you to read our tutorials and learn more about
55
  [SpeechBrain](https://speechbrain.github.io).
56
 
57
- ### Transcribing your own audio files (in French)
58
 
59
  ```python
60
  from speechbrain.pretrained import EncoderDecoderASR
61
- asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/speechbrain/asr-transducer-commonvoice-14-fr", savedir="pretrained_models/speechbrain/asr-transducer-commonvoice-14-fr")
62
- asr_model.transcribe_file("speechbrain/speechbrain/asr-transducer-commonvoice-14-fr/example-fr.wav")
63
  ```
64
 
65
  ### Inference on GPU
@@ -93,10 +93,10 @@ pip install -e .
93
 
94
  ```
95
  cd recipes/CommonVoice/ASR/transducer
96
- python train.py hparams/train_fr.yaml --data_folder=your_data_folder
97
  ```
98
 
99
- You can find our training results (models, logs, etc) [here](https://www.dropbox.com/sh/nv2pnpo5n3besn3/AADZ7l41oLt11ZuOE4MqoJhCa?dl=0)
100
 
101
  ### Limitations
102
 
 
1
  ---
2
  language:
3
+ - de
4
  thumbnail: null
5
  tags:
6
  - automatic-speech-recognition
 
14
  metrics:
15
  - name: Test WER
16
  type: wer
17
+ value: ' 15.25'
18
  ---
19
 
20
  <iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
21
  <br/><br/>
22
 
23
+ # Transducer trained on CommonVoice 14.0 German (No LM)
24
  This repository provides all the necessary tools to perform automatic speech
25
  recognition from an end-to-end system within
26
  SpeechBrain. For a better experience, we encourage you to learn more about
 
29
 
30
  | Release | Test CER | Test WER | GPUs |
31
  |:-------------:|:--------------:|:--------------:| :--------:|
32
+ | 15.08.23 | 5.43 | 15.25 | 1xV100 32GB |
33
 
34
  ## Credits
35
  The model is provided by [vitas.ai](https://www.vitas.ai/).
 
54
  Please notice that we encourage you to read our tutorials and learn more about
55
  [SpeechBrain](https://speechbrain.github.io).
56
 
57
+ ### Transcribing your own audio files (in German)
58
 
59
  ```python
60
  from speechbrain.pretrained import EncoderDecoderASR
61
+ asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/speechbrain/asr-transducer-commonvoice-14-de", savedir="pretrained_models/speechbrain/asr-transducer-commonvoice-14-de")
62
+ asr_model.transcribe_file("speechbrain/speechbrain/asr-transducer-commonvoice-14-de/example-de.wav")
63
  ```
64
 
65
  ### Inference on GPU
 
93
 
94
  ```
95
  cd recipes/CommonVoice/ASR/transducer
96
+ python train.py hparams/train_de.yaml --data_folder=your_data_folder
97
  ```
98
 
99
+ You can find our training results (models, logs, etc) [here](https://www.dropbox.com/sh/jfge6ixbtoje64t/AADeAgL5un0A8uEjPSM84ex8a?dl=0)
100
 
101
  ### Limitations
102