Update README.md
Browse files
README.md
CHANGED
@@ -29,8 +29,8 @@ model-index:
|
|
29 |
# Whisper Tiny it 8
|
30 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
-
- Loss:
|
33 |
-
- Wer:
|
34 |
|
35 |
## Model description
|
36 |
|
@@ -62,12 +62,12 @@ The following hyperparameters were used during training:
|
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
- lr_scheduler_warmup_steps: 500
|
65 |
-
- training_steps:
|
66 |
- mixed_precision_training: Native AMP
|
67 |
### Training results
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
-
| 0.
|
71 |
### Framework versions
|
72 |
- Transformers 4.26.0.dev0
|
73 |
- Pytorch 1.12.1+cu113
|
|
|
29 |
# Whisper Tiny it 8
|
30 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 1.011502
|
33 |
+
- Wer: 56.905158
|
34 |
|
35 |
## Model description
|
36 |
|
|
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
- lr_scheduler_warmup_steps: 500
|
65 |
+
- training_steps: 3000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
### Training results
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
+
| 0.525800 | 3.82 | 3000 | 1.011502 |56.905158|
|
71 |
### Framework versions
|
72 |
- Transformers 4.26.0.dev0
|
73 |
- Pytorch 1.12.1+cu113
|