metadata
language:
- sr
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
- google/fleurs
- Sagicc/audio-lmb-ds
- classla/ParlaSpeech-RS
metrics:
- wer
model-index:
- name: Whisper Base Sr
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13
type: mozilla-foundation/common_voice_16_0
config: sr
split: test
args: sr
metrics:
- name: Wer
type: wer
value: 0.27887672200635816
Whisper Base Sr
This model is a fine-tuned version of openai/whisper-base on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3129
- Wer Ortho: 0.3801
- Wer: 0.2789
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.4839 | 0.03 | 500 | 0.4684 | 0.5407 | 0.4170 |
| 0.4084 | 0.05 | 1000 | 0.3948 | 0.4578 | 0.3559 |
| 0.3873 | 0.08 | 1500 | 0.3690 | 0.4276 | 0.3260 |
| 0.3562 | 0.11 | 2000 | 0.3450 | 0.4129 | 0.3117 |
| 0.3233 | 0.13 | 2500 | 0.3293 | 0.3935 | 0.2912 |
| 0.313 | 0.16 | 3000 | 0.3232 | 0.3887 | 0.2861 |
| 0.3062 | 0.19 | 3500 | 0.3158 | 0.3866 | 0.2851 |
| 0.3154 | 0.22 | 4000 | 0.3129 | 0.3801 | 0.2789 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1