End of training
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: whisper-small-akan
|
| 9 |
results: []
|
|
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# whisper-small-akan
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -40,9 +45,23 @@ The following hyperparameters were used during training:
|
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- lr_scheduler_warmup_steps: 200
|
| 43 |
-
- training_steps:
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.44.2
|
|
|
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: whisper-small-akan
|
| 11 |
results: []
|
|
|
|
| 17 |
# whisper-small-akan
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2208
|
| 22 |
+
- Wer: 9.3196
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 200
|
| 48 |
+
- training_steps: 2000
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 55 |
+
| 0.0726 | 10.0 | 250 | 0.8217 | 48.0395 |
|
| 56 |
+
| 0.0246 | 20.0 | 500 | 0.9650 | 44.0903 |
|
| 57 |
+
| 0.011 | 30.0 | 750 | 0.9165 | 40.6770 |
|
| 58 |
+
| 0.0022 | 40.0 | 1000 | 0.9419 | 39.9436 |
|
| 59 |
+
| 0.0009 | 50.0 | 1250 | 0.2120 | 9.7770 |
|
| 60 |
+
| 0.0002 | 60.0 | 1500 | 0.2179 | 9.0909 |
|
| 61 |
+
| 0.0001 | 70.0 | 1750 | 0.2201 | 9.3196 |
|
| 62 |
+
| 0.0001 | 80.0 | 2000 | 0.2208 | 9.3196 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- Transformers 4.44.2
|