metadata
language:
- id
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_12_0
metrics:
- wer
model-index:
- name: Whisper tiny ID - Augmented
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_12_0
type: mozilla-foundation/common_voice_12_0
config: id
split: test
args: id
metrics:
- name: Wer
type: wer
value: 21.475261506718418
Whisper tiny ID - Augmented
This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_12_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4667
- Wer: 21.4753
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: 1
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.112 | 0.02 | 200 | 0.7991 | 49.6689 |
| 1.116 | 0.05 | 400 | 0.7007 | 63.0457 |
| 1.1079 | 0.07 | 600 | 0.6334 | 34.6170 |
| 0.9625 | 0.1 | 800 | 0.5313 | 25.3744 |
| 0.7697 | 0.12 | 1000 | 0.4667 | 21.4753 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2