metadata
language:
- uk
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Medium uk
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: uk
split: test
args: uk
metrics:
- name: Wer
type: wer
value: 10.912533864101288
Whisper Medium uk
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2943
- Wer: 10.9125
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: 32
- 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: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2039 | 0.9099 | 1000 | 0.2393 | 14.0916 |
| 0.0942 | 1.8198 | 2000 | 0.2207 | 11.8428 |
| 0.0463 | 2.7298 | 3000 | 0.2303 | 11.5953 |
| 0.0156 | 3.6397 | 4000 | 0.2701 | 11.0438 |
| 0.0041 | 4.5496 | 5000 | 0.2943 | 10.9125 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1