metadata
language:
- mn
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Mn - 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: mn
split: None
args: 'config: mn, split: test'
metrics:
- name: Wer
type: wer
value: 46.60332022717344
Whisper Small Mn - 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: 0.5062
- Wer: 46.6033
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: 2
- 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: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6115 | 0.4975 | 1000 | 0.7317 | 69.4572 |
| 0.4096 | 0.9950 | 2000 | 0.5577 | 56.7770 |
| 0.2114 | 1.4925 | 3000 | 0.5270 | 52.8506 |
| 0.2126 | 1.9900 | 4000 | 0.4860 | 50.1365 |
| 0.105 | 2.4876 | 5000 | 0.5017 | 48.1542 |
| 0.0678 | 2.9851 | 6000 | 0.4909 | 47.1876 |
| 0.0294 | 3.4826 | 7000 | 0.5062 | 46.6033 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1