poonehmousavi
commited on
Commit
•
1fe29cd
1
Parent(s):
c0583ea
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
-
|
4 |
thumbnail: null
|
5 |
pipeline_tag: automatic-speech-recognition
|
6 |
tags:
|
@@ -16,31 +16,31 @@ metrics:
|
|
16 |
- wer
|
17 |
- cer
|
18 |
model-index:
|
19 |
-
- name: asr-whisper-medium-commonvoice-
|
20 |
results:
|
21 |
- task:
|
22 |
name: Automatic Speech Recognition
|
23 |
type: automatic-speech-recognition
|
24 |
dataset:
|
25 |
-
name: CommonVoice 10.0 (
|
26 |
type: mozilla-foundation/common_voice_14_0
|
27 |
-
config:
|
28 |
split: test
|
29 |
args:
|
30 |
-
language:
|
31 |
metrics:
|
32 |
- name: Test WER
|
33 |
type: wer
|
34 |
-
value: '
|
35 |
---
|
36 |
|
37 |
<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=medium" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
|
38 |
<br/><br/>
|
39 |
|
40 |
-
# whisper medium fine-tuned on CommonVoice-14.0
|
41 |
|
42 |
This repository provides all the necessary tools to perform automatic speech
|
43 |
-
recognition from an end-to-end whisper model fine-tuned on CommonVoice (
|
44 |
SpeechBrain. For a better experience, we encourage you to learn more about
|
45 |
[SpeechBrain](https://speechbrain.github.io).
|
46 |
|
@@ -48,7 +48,7 @@ The performance of the model is the following:
|
|
48 |
|
49 |
| Release | Test CER | Test WER | GPUs |
|
50 |
|:-------------:|:--------------:|:--------------:| :--------:|
|
51 |
-
| 1-08-23 |
|
52 |
|
53 |
## Pipeline description
|
54 |
|
@@ -72,14 +72,14 @@ pip install speechbrain transformers
|
|
72 |
Please notice that we encourage you to read our tutorials and learn more about
|
73 |
[SpeechBrain](https://speechbrain.github.io).
|
74 |
|
75 |
-
### Transcribing your own audio files (in
|
76 |
|
77 |
```python
|
78 |
|
79 |
from speechbrain.pretrained import WhisperASR
|
80 |
|
81 |
-
asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-medium-commonvoice-
|
82 |
-
asr_model.transcribe_file("speechbrain/asr-whisper-lmedium-commonvoice-
|
83 |
|
84 |
|
85 |
```
|
@@ -103,7 +103,7 @@ pip install -e .
|
|
103 |
3. Run Training:
|
104 |
```bash
|
105 |
cd recipes/CommonVoice/ASR/transformer/
|
106 |
-
python train_with_whisper.py hparams/
|
107 |
```
|
108 |
|
109 |
You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/11PKCsyIE703mmDv6n6n_UnD0bUgMPbg_?usp=share_link).
|
|
|
1 |
---
|
2 |
language:
|
3 |
+
- fa
|
4 |
thumbnail: null
|
5 |
pipeline_tag: automatic-speech-recognition
|
6 |
tags:
|
|
|
16 |
- wer
|
17 |
- cer
|
18 |
model-index:
|
19 |
+
- name: asr-whisper-medium-commonvoice-fa
|
20 |
results:
|
21 |
- task:
|
22 |
name: Automatic Speech Recognition
|
23 |
type: automatic-speech-recognition
|
24 |
dataset:
|
25 |
+
name: CommonVoice 10.0 (Farsi)
|
26 |
type: mozilla-foundation/common_voice_14_0
|
27 |
+
config: fa
|
28 |
split: test
|
29 |
args:
|
30 |
+
language: fa
|
31 |
metrics:
|
32 |
- name: Test WER
|
33 |
type: wer
|
34 |
+
value: '29.01'
|
35 |
---
|
36 |
|
37 |
<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=medium" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
|
38 |
<br/><br/>
|
39 |
|
40 |
+
# whisper medium fine-tuned on CommonVoice-14.0 Farsi
|
41 |
|
42 |
This repository provides all the necessary tools to perform automatic speech
|
43 |
+
recognition from an end-to-end whisper model fine-tuned on CommonVoice (Fasri Language) within
|
44 |
SpeechBrain. For a better experience, we encourage you to learn more about
|
45 |
[SpeechBrain](https://speechbrain.github.io).
|
46 |
|
|
|
48 |
|
49 |
| Release | Test CER | Test WER | GPUs |
|
50 |
|:-------------:|:--------------:|:--------------:| :--------:|
|
51 |
+
| 1-08-23 | 8.58 | 29.01 | 1xV100 32GB |
|
52 |
|
53 |
## Pipeline description
|
54 |
|
|
|
72 |
Please notice that we encourage you to read our tutorials and learn more about
|
73 |
[SpeechBrain](https://speechbrain.github.io).
|
74 |
|
75 |
+
### Transcribing your own audio files (in Farsi)
|
76 |
|
77 |
```python
|
78 |
|
79 |
from speechbrain.pretrained import WhisperASR
|
80 |
|
81 |
+
asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-medium-commonvoice-fa", savedir="pretrained_models/asr-whisper-medium-commonvoice-fa")
|
82 |
+
asr_model.transcribe_file("speechbrain/asr-whisper-lmedium-commonvoice-fa/example-fa.mp3")
|
83 |
|
84 |
|
85 |
```
|
|
|
103 |
3. Run Training:
|
104 |
```bash
|
105 |
cd recipes/CommonVoice/ASR/transformer/
|
106 |
+
python train_with_whisper.py hparams/train_fa_hf_whisper.yaml --data_folder=your_data_folder
|
107 |
```
|
108 |
|
109 |
You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/11PKCsyIE703mmDv6n6n_UnD0bUgMPbg_?usp=share_link).
|