metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- wer
model-index:
- name: whisper-small-hi
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: minds14
type: minds14
config: en-US
split: None
args: en-US
metrics:
- name: Wer
type: wer
value: 23.117960877296976
whisper-small-hi
This model is a fine-tuned version of openai/whisper-small on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6055
- Wer: 23.1180
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1178 | 1.0 | 57 | 1.1225 | 115.5898 |
| 0.7581 | 2.0 | 114 | 0.6572 | 50.2075 |
| 0.3468 | 3.0 | 171 | 0.5129 | 27.6823 |
| 0.221 | 4.0 | 228 | 0.4969 | 23.2365 |
| 0.1407 | 5.0 | 285 | 0.5054 | 24.0071 |
| 0.08 | 6.0 | 342 | 0.5423 | 25.3705 |
| 0.0395 | 7.0 | 399 | 0.5861 | 22.1695 |
| 0.0194 | 8.0 | 456 | 0.5858 | 24.3628 |
| 0.0221 | 8.7719 | 500 | 0.6055 | 23.1180 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0