metadata
language:
- multilingual
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: basic_train_basic_test_shuffle_250 300 1200 300 300
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: xbilek25/basic_train_basic_test_shuffle_250
type: mozilla-foundation/common_voice_11_0
args: 'config: csen, split: train'
metrics:
- name: Wer
type: wer
value: 18.07865388378008
basic_train_basic_test_shuffle_250 300 1200 300 300
This model is a fine-tuned version of openai/whisper-small on the xbilek25/basic_train_basic_test_shuffle_250 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0982
- Wer: 18.0787
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: 300
- training_steps: 1200
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.0006 | 2.04 | 300 | 0.0969 | 26.1006 |
0.0004 | 4.08 | 600 | 0.0986 | 25.1810 |
0.0002 | 7.02 | 900 | 0.0978 | 26.5310 |
0.0002 | 9.06 | 1200 | 0.0982 | 18.0787 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2