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 - Sanchit Gandhi
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: test
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 65.9189029035808
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: 0.5964
- Wer: 65.9189
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: 50
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9954 | 0.02 | 10 | 2.0896 | 111.0937 |
| 1.4388 | 0.05 | 20 | 1.4497 | 106.8780 |
| 1.0201 | 0.07 | 30 | 0.9971 | 110.6281 |
| 0.7901 | 0.1 | 40 | 0.8241 | 80.4199 |
| 0.6572 | 0.12 | 50 | 0.7474 | 95.7039 |
| 0.6096 | 0.15 | 60 | 0.6896 | 85.3890 |
| 0.5228 | 0.17 | 70 | 0.6508 | 75.9672 |
| 0.5413 | 0.2 | 80 | 0.6219 | 67.5527 |
| 0.5319 | 0.22 | 90 | 0.6047 | 67.7516 |
| 0.4952 | 0.24 | 100 | 0.5964 | 65.9189 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2