metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: whisper-small-fa
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: fa
split: test
args: fa
metrics:
- name: Wer
type: wer
value: 35.00088651273169
whisper-small-fa
This model is a fine-tuned version of openai/whisper-small on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.3028
- Wer: 35.0009
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: 16
- 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: 500000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0053 | 40.5515 | 100000 | 0.8333 | 36.2993 |
| 0.0011 | 81.1030 | 200000 | 1.0030 | 35.9242 |
| 0.0008 | 121.6545 | 300000 | 1.0865 | 35.6501 |
| 0.0 | 162.2060 | 400000 | 1.1741 | 35.4823 |
| 0.0 | 202.7575 | 500000 | 1.3028 | 35.0009 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1