metadata
language:
- ml
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_14_0
metrics:
- wer
model-index:
- name: Whisper Small Malayalam - Arjun Shaji
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13.0
type: mozilla-foundation/common_voice_14_0
config: ml
split: None
args: 'config: ml, split: test'
metrics:
- name: Wer
type: wer
value: 72.38930659983292
Whisper Small Malayalam - Arjun Shaji
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4878
- Wer: 72.3893
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0081 | 9.6154 | 1000 | 0.3642 | 73.2665 |
| 0.0019 | 19.2308 | 2000 | 0.4225 | 71.8045 |
| 0.0002 | 28.8462 | 3000 | 0.4564 | 73.3918 |
| 0.0 | 38.4615 | 4000 | 0.4809 | 72.5564 |
| 0.0 | 48.0769 | 5000 | 0.4878 | 72.3893 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1