metadata
license: apache-2.0
language:
- tg
tags:
- generated_from_trainer
- whisper-event
- hf-asr-leaderboard
metrics:
- wer
model-index:
- name: whisper-small-tg
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: google/fleurs
type: google/fleurs
config: tg_tj
split: test
args: tg_tj
metrics:
- name: Wer
type: wer
value: 28.3622
whisper-small-tg
This model is a fine-tuned version of openai/whisper-small on the google/fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6917
- Wer: 28.3622
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: 64
- eval_batch_size: 32
- 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 | Wer |
|---|---|---|---|---|
| 0.0011 | 25.0 | 1000 | 0.5801 | 28.1310 |
| 0.0004 | 50.0 | 2000 | 0.6423 | 28.2620 |
| 0.0002 | 75.0 | 3000 | 0.6796 | 28.3931 |
| 0.0002 | 100.0 | 4000 | 0.6917 | 28.3622 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2