metadata
language:
- ur
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- common_voice_16_0
model-index:
- name: ft_model
results: []
ft_model
This model is a fine-tuned version of openai/whisper-base on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.6440
- Cer: 17.7300
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: 1
- eval_batch_size: 1
- 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 | Cer |
|---|---|---|---|---|
| 0.7421 | 0.19 | 1000 | 0.7957 | 22.9425 |
| 0.5741 | 0.37 | 2000 | 0.7230 | 20.7530 |
| 0.4998 | 0.56 | 3000 | 0.6686 | 19.8136 |
| 0.7295 | 0.75 | 4000 | 0.6440 | 17.7300 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0