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 Jsun Hi - Jiping
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: 31.761618555828324
Whisper Small Jsun Hi - Jiping
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: 0.2775
- Wer: 31.7616
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2092 | 0.61 | 1000 | 0.3201 | 38.7666 |
| 0.1106 | 1.22 | 2000 | 0.2810 | 34.1023 |
| 0.1049 | 1.83 | 3000 | 0.2660 | 32.4812 |
| 0.052 | 2.45 | 4000 | 0.2775 | 31.7616 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1