metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Small Hi -MUKUND
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_17_0
config: te
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 87.36263736263736
Whisper Small Hi -MUKUND
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0257
- Wer: 87.3626
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 |
|---|---|---|---|---|
| 0.0 | 142.8571 | 1000 | 0.7698 | 86.8132 |
| 0.0 | 285.7143 | 2000 | 0.8781 | 87.9121 |
| 0.0 | 428.5714 | 3000 | 0.9771 | 87.3626 |
| 0.0 | 571.4286 | 4000 | 1.0257 | 87.3626 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1