metadata
language:
- fa
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
metrics:
- wer
model-index:
- name: Whisper Small Fa - Brett OConnor
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 16.0
type: mozilla-foundation/common_voice_16_0
config: fa
split: None
args: 'config: fa, split: test'
metrics:
- name: Wer
type: wer
value: 36.47368708374277
Whisper Small Fa - Brett OConnor
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3430
- Wer: 36.4737
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: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2624 | 0.41 | 1000 | 0.4720 | 46.3383 |
| 0.2143 | 0.81 | 2000 | 0.4001 | 41.8932 |
| 0.1133 | 1.22 | 3000 | 0.3755 | 38.6805 |
| 0.1196 | 1.63 | 4000 | 0.3492 | 36.6661 |
| 0.0729 | 2.03 | 5000 | 0.3430 | 36.4737 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2