update model card README.md
Browse files
README.md
CHANGED
@@ -15,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# wav2vec2-base-gn-demo
|
16 |
|
17 |
This model is a fine-tuned version of [azuur/wav2vec2-base-gn-demo](https://huggingface.co/azuur/wav2vec2-base-gn-demo) on the common_voice dataset.
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,10 +42,31 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: cosine_with_restarts
|
42 |
-
- lr_scheduler_warmup_steps:
|
43 |
-
- num_epochs:
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
### Framework versions
|
47 |
|
48 |
- Transformers 4.11.3
|
|
|
15 |
# wav2vec2-base-gn-demo
|
16 |
|
17 |
This model is a fine-tuned version of [azuur/wav2vec2-base-gn-demo](https://huggingface.co/azuur/wav2vec2-base-gn-demo) on the common_voice dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7426
|
20 |
+
- Wer: 0.7256
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: cosine_with_restarts
|
45 |
+
- lr_scheduler_warmup_steps: 50
|
46 |
+
- num_epochs: 60
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| No log | 4.0 | 100 | 0.7045 | 0.7409 |
|
54 |
+
| No log | 8.0 | 200 | 0.7200 | 0.75 |
|
55 |
+
| No log | 12.0 | 300 | 0.7400 | 0.7439 |
|
56 |
+
| No log | 16.0 | 400 | 0.7677 | 0.7515 |
|
57 |
+
| 0.0846 | 20.0 | 500 | 0.7765 | 0.7271 |
|
58 |
+
| 0.0846 | 24.0 | 600 | 0.7821 | 0.7287 |
|
59 |
+
| 0.0846 | 28.0 | 700 | 0.7671 | 0.7180 |
|
60 |
+
| 0.0846 | 32.0 | 800 | 0.7594 | 0.7180 |
|
61 |
+
| 0.0846 | 36.0 | 900 | 0.7500 | 0.7165 |
|
62 |
+
| 0.0713 | 40.0 | 1000 | 0.7351 | 0.7287 |
|
63 |
+
| 0.0713 | 44.0 | 1100 | 0.7361 | 0.7241 |
|
64 |
+
| 0.0713 | 48.0 | 1200 | 0.7389 | 0.7378 |
|
65 |
+
| 0.0713 | 52.0 | 1300 | 0.7424 | 0.7210 |
|
66 |
+
| 0.0713 | 56.0 | 1400 | 0.7425 | 0.7256 |
|
67 |
+
| 0.0669 | 60.0 | 1500 | 0.7426 | 0.7256 |
|
68 |
+
|
69 |
+
|
70 |
### Framework versions
|
71 |
|
72 |
- Transformers 4.11.3
|