metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- peterwei89/hindi_project1
metrics:
- wer
model-index:
- name: Whisper Small hindi - Peter Wei
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: hindi_project1
type: peterwei89/hindi_project1
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 34.13612122238212
Whisper Small hindi - Peter Wei
This model is a fine-tuned version of openai/whisper-small on the hindi_project1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4301
- Wer: 34.1361
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.082 | 2.44 | 1000 | 0.2958 | 35.3213 |
| 0.0221 | 4.89 | 2000 | 0.3454 | 33.7806 |
| 0.0013 | 7.33 | 3000 | 0.4056 | 34.1531 |
| 0.0005 | 9.78 | 4000 | 0.4301 | 34.1361 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0