metadata
language:
- bn
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
base_model: openai/whisper-small
model-index:
- name: Whisper Small Hi - Sanchit Gandhi
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
args: 'config: hi, split: test'
metrics:
- type: wer
value: 40.38828355674009
name: Wer
Whisper Small Hi - Sanchit Gandhi
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: 0.1305
- Wer: 40.3883
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: 4
- 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 |
|---|---|---|---|---|
| 0.1994 | 0.16 | 1000 | 0.2302 | 58.9519 |
| 0.1424 | 0.32 | 2000 | 0.1697 | 48.0494 |
| 0.1379 | 0.48 | 3000 | 0.1434 | 43.1854 |
| 0.1209 | 0.64 | 4000 | 0.1305 | 40.3883 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1