metadata
language:
- az
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- seyidov579/azerbaijan
metrics:
- wer
model-index:
- name: Whisper Tiny Az - Kenan Seyidov
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13.0
type: seyidov579/azerbaijan
config: az_az
split: test
args: 'config: az, split: test'
metrics:
- name: Wer
type: wer
value: 100
Whisper Tiny Az - Kenan Seyidov
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.5260
- Wer: 100.0
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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 1000.0 | 1000 | 2.3577 | 100.0 |
| 0.0 | 2000.0 | 2000 | 2.4623 | 100.0 |
| 0.0 | 3000.0 | 3000 | 2.5096 | 100.0 |
| 0.0 | 4000.0 | 4000 | 2.5260 | 100.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3