metadata
base_model: openai/whisper-tiny
datasets:
- mozilla-foundation/common_voice_11_0
language:
- az
license: apache-2.0
metrics:
- wer
tags:
- hf-asr-leaderboard
- generated_from_trainer
model-index:
- name: Whisper Tiny Az - Pologue
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: az
split: None
args: 'config: az, split: test'
metrics:
- type: wer
value: 118.18181818181819
name: Wer
Whisper Tiny Az - Pologue
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.5076
- Wer: 118.1818
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: 50
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.0177 | 33.3333 | 100 | 1.5076 | 118.1818 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cpu
- Datasets 2.20.0
- Tokenizers 0.19.1