metadata
license: mit
base_model: distil-whisper/distil-small.en
tags:
- generated_from_trainer
datasets:
- speech_commands
metrics:
- accuracy
model-index:
- name: distil-small.en-speech-commands
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: speech_commands
type: speech_commands
config: v0.02
split: None
args: v0.02
metrics:
- name: Accuracy
type: accuracy
value: 0.8066546762589928
distil-small.en-speech-commands
This model is a fine-tuned version of distil-whisper/distil-small.en on the speech_commands dataset. It achieves the following results on the evaluation set:
- Loss: 0.9307
- Accuracy: 0.8067
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1861 | 1.0 | 618 | 0.7743 | 0.8022 |
| 0.1135 | 2.0 | 1236 | 0.9853 | 0.8049 |
| 0.078 | 3.0 | 1854 | 0.9307 | 0.8067 |
| 0.038 | 4.0 | 2472 | 0.9989 | 0.8049 |
| 0.0375 | 5.0 | 3090 | 1.0738 | 0.8035 |
| 0.0462 | 6.0 | 3708 | 1.1601 | 0.8067 |
| 0.018 | 7.0 | 4326 | 1.5369 | 0.8067 |
| 0.0008 | 8.0 | 4944 | 1.2515 | 0.8067 |
| 0.0016 | 9.0 | 5562 | 1.3494 | 0.8058 |
| 0.0002 | 10.0 | 6180 | 1.5117 | 0.8053 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1