Model save
Browse files
README.md
CHANGED
|
@@ -4,8 +4,6 @@ license: mit
|
|
| 4 |
base_model: distil-whisper/distil-small.en
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
datasets:
|
| 8 |
-
- generator
|
| 9 |
model-index:
|
| 10 |
- name: distil_whisper_en
|
| 11 |
results: []
|
|
@@ -16,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# distil_whisper_en
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [distil-whisper/distil-small.en](https://huggingface.co/distil-whisper/distil-small.en) on the
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -36,15 +34,15 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0001
|
| 39 |
-
- train_batch_size:
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
-
- gradient_accumulation_steps:
|
| 43 |
-
- total_train_batch_size:
|
| 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
|
|
|
|
| 4 |
base_model: distil-whisper/distil-small.en
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: distil_whisper_en
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# distil_whisper_en
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [distil-whisper/distil-small.en](https://huggingface.co/distil-whisper/distil-small.en) on the None dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 0.0001
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
+
- total_train_batch_size: 32
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 800
|
| 45 |
+
- training_steps: 350
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|