End of training
Browse files
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Wer:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,18 +43,19 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- lr_scheduler_warmup_steps:
|
47 |
-
- training_steps:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0317
|
21 |
+
- Wer: 16.4220
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 1000
|
47 |
+
- training_steps: 5000
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
54 |
+
| 0.0595 | 0.4 | 1000 | 0.0904 | 42.5230 |
|
55 |
+
| 0.0339 | 0.79 | 2000 | 0.0593 | 30.1319 |
|
56 |
+
| 0.0171 | 1.19 | 3000 | 0.0441 | 23.5133 |
|
57 |
+
| 0.0133 | 1.58 | 4000 | 0.0363 | 19.1092 |
|
58 |
+
| 0.0096 | 1.98 | 5000 | 0.0317 | 16.4220 |
|
59 |
|
60 |
|
61 |
### Framework versions
|