Update README.md
Browse files
README.md
CHANGED
|
@@ -40,8 +40,6 @@ This model achieves the following results on the evaluation set:
|
|
| 40 |
- Wer: 28.2995
|
| 41 |
- Cer: 10.8968
|
| 42 |
|
| 43 |
-
Finetuning code avaiblable in https://github.com/ixxan/ug-speech
|
| 44 |
-
|
| 45 |
## Training and evaluation data
|
| 46 |
|
| 47 |
The training was done using the combined train and dev set of common_voice_15_0 (11215 recordings, \~20hrs of audio).
|
|
@@ -50,6 +48,8 @@ The testing was done using the test set of THUYG20 as the standard benchmark for
|
|
| 50 |
|
| 51 |
## Training procedure
|
| 52 |
|
|
|
|
|
|
|
| 53 |
### Training hyperparameters
|
| 54 |
|
| 55 |
The following hyperparameters were used during training:
|
|
|
|
| 40 |
- Wer: 28.2995
|
| 41 |
- Cer: 10.8968
|
| 42 |
|
|
|
|
|
|
|
| 43 |
## Training and evaluation data
|
| 44 |
|
| 45 |
The training was done using the combined train and dev set of common_voice_15_0 (11215 recordings, \~20hrs of audio).
|
|
|
|
| 48 |
|
| 49 |
## Training procedure
|
| 50 |
|
| 51 |
+
Finetuning code avaiblable in https://github.com/ixxan/ug-speech
|
| 52 |
+
|
| 53 |
### Training hyperparameters
|
| 54 |
|
| 55 |
The following hyperparameters were used during training:
|