metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Tiny Hindi - Sainadh Vatturi
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: hi
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 60.9667315669178
Whisper Tiny Hindi - Sainadh Vatturi
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6314
- Wer: 60.9667
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 |
---|---|---|---|---|
0.308 | 2.44 | 1000 | 0.5337 | 63.8238 |
0.1876 | 4.89 | 2000 | 0.5105 | 59.3287 |
0.0936 | 7.33 | 3000 | 0.5599 | 59.4853 |
0.0657 | 9.78 | 4000 | 0.6047 | 60.3699 |
0.0466 | 12.22 | 5000 | 0.6314 | 60.9667 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2