Commit
·
a063758
1
Parent(s):
1d00c31
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: wav2vec2-large-asr-th
|
| 7 |
results: []
|
|
@@ -12,7 +14,11 @@ 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-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -41,6 +47,22 @@ The following hyperparameters were used during training:
|
|
| 41 |
- training_steps: 2000
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.26.1
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
model-index:
|
| 8 |
- name: wav2vec2-large-asr-th
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# wav2vec2-large-asr-th
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3903
|
| 20 |
+
- Wer: 1.0
|
| 21 |
+
- Cer: 0.9442
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 47 |
- training_steps: 2000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|:------:|
|
| 54 |
+
| 3.9178 | 1.09 | 200 | 4.1261 | 1.0 | 1.0000 |
|
| 55 |
+
| 3.7661 | 2.19 | 400 | 3.8671 | 1.0 | 1.0000 |
|
| 56 |
+
| 3.7807 | 3.28 | 600 | 3.7873 | 1.0 | 1.0000 |
|
| 57 |
+
| 3.7099 | 4.37 | 800 | 3.7331 | 1.0 | 1.0000 |
|
| 58 |
+
| 3.4771 | 5.46 | 1000 | 3.3761 | 1.0 | 0.9998 |
|
| 59 |
+
| 2.5528 | 6.56 | 1200 | 2.2584 | 1.0 | 0.9637 |
|
| 60 |
+
| 1.9769 | 7.65 | 1400 | 1.7215 | 1.0 | 0.9507 |
|
| 61 |
+
| 1.716 | 8.74 | 1600 | 1.5033 | 1.0 | 0.9464 |
|
| 62 |
+
| 1.5803 | 9.84 | 1800 | 1.3903 | 1.0 | 0.9442 |
|
| 63 |
+
| 1.4613 | 10.93 | 2000 | 1.3541 | 1.0 | 0.9433 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.26.1
|