Commit
•
f53dec6
1
Parent(s):
5d9584e
update model card README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# wav2vec2-large-asr-th
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -43,6 +46,15 @@ The following hyperparameters were used during training:
|
|
| 43 |
- training_steps: 1500
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.26.0
|
|
|
|
| 12 |
|
| 13 |
# wav2vec2-large-asr-th
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.8773
|
| 18 |
+
- Cer: 0.9999
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 46 |
- training_steps: 1500
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 5.2461 | 4.39 | 400 | 5.0687 | 0.9999 |
|
| 54 |
+
| 4.0581 | 8.79 | 800 | 4.0428 | 0.9999 |
|
| 55 |
+
| 3.962 | 13.19 | 1200 | 3.8773 | 0.9999 |
|
| 56 |
+
|
| 57 |
+
|
| 58 |
### Framework versions
|
| 59 |
|
| 60 |
- Transformers 4.26.0
|