metadata
language:
- hi
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Hi - Naga Budigam
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 42.69448912215356
Whisper Small Hi - Naga Budigam
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: 0.3620
- Wer: 42.6945
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: 4
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5719 | 0.06 | 100 | 0.6811 | 79.3913 |
| 0.4096 | 0.12 | 200 | 0.4827 | 62.2492 |
| 0.3104 | 0.18 | 300 | 0.3839 | 44.1167 |
| 0.2728 | 0.24 | 400 | 0.3620 | 42.6945 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2