Update README.md
Browse files
README.md
CHANGED
@@ -17,8 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [CGN dataset](https://taalmaterialen.ivdnt.org/download/tstc-corpus-gesproken-nederlands/).
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
-
|
21 |
-
- Wer: 19.8814
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -44,7 +43,7 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 50
|
47 |
-
- training_steps:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
@@ -61,6 +60,11 @@ The following hyperparameters were used during training:
|
|
61 |
| 0.6066 | 0.8 | 800 | 0.3804 | 19.2748 |
|
62 |
| 0.2075 | 1.09 | 900 | 0.3794 | 18.8904 |
|
63 |
| 0.2102 | 1.19 | 1000 | 0.3777 | 19.8814 |
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [CGN dataset](https://taalmaterialen.ivdnt.org/download/tstc-corpus-gesproken-nederlands/).
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Wer: 15.8367
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 50
|
46 |
+
- training_steps: 6000
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
|
|
60 |
| 0.6066 | 0.8 | 800 | 0.3804 | 19.2748 |
|
61 |
| 0.2075 | 1.09 | 900 | 0.3794 | 18.8904 |
|
62 |
| 0.2102 | 1.19 | 1000 | 0.3777 | 19.8814 |
|
63 |
+
| 0.2045 | 2.49 | 2000 | 0.3194 | 16.1628 |
|
64 |
+
| 0.0652 | 4.97 | 3000 | 0.3425 | 16.3672 |
|
65 |
+
| 0.0167 | 7.46 | 4000 | 0.3915 | 15.8187 |
|
66 |
+
| 0.0064 | 9.95 | 5000 | 0.4190 | 15.7298 |
|
67 |
+
| 0.0041 | 12.44 | 6000 | 0.4315 | 15.8367 |
|
68 |
|
69 |
|
70 |
### Framework versions
|