metadata
base_model: openai/whisper-medium
datasets:
- google/fleurs
language:
- hi
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: Whisper Medium Hindi -megha sharma
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Google Fleurs
type: google/fleurs
config: hi_in
split: None
args: 'config: hi, split: test'
metrics:
- type: wer
value: 18.44006247559547
name: Wer
Whisper Medium Hindi -megha sharma
This model is a fine-tuned version of openai/whisper-medium on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.3508
- Wer: 18.4401
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-06
- train_batch_size: 8
- 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: 1000
- training_steps: 15000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0669 | 3.3898 | 1000 | 0.2077 | 20.9098 |
| 0.0118 | 6.7797 | 2000 | 0.2657 | 19.4162 |
| 0.0026 | 10.1695 | 3000 | 0.2930 | 18.9477 |
| 0.0018 | 13.5593 | 4000 | 0.3045 | 18.3717 |
| 0.0017 | 16.9492 | 5000 | 0.3281 | 18.7134 |
| 0.0011 | 20.3390 | 6000 | 0.3288 | 18.1179 |
| 0.0005 | 23.7288 | 7000 | 0.3398 | 18.3034 |
| 0.0004 | 27.1186 | 8000 | 0.3515 | 18.5182 |
| 0.0003 | 30.5085 | 9000 | 0.3508 | 18.4401 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1