metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: whisper-medium-fa
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: fa
split: None
args: fa
metrics:
- name: Wer
type: wer
value: 40.872328527979704
whisper-medium-fa
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: 0.4233
- Wer: 40.8723
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: 1000
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3796 | 0.0811 | 200 | 0.5452 | 47.2661 |
| 0.3085 | 0.1622 | 400 | 0.4883 | 44.2043 |
| 0.2575 | 0.2433 | 600 | 0.4480 | 43.2045 |
| 0.2283 | 0.3244 | 800 | 0.4262 | 40.0376 |
| 0.246 | 0.4055 | 1000 | 0.4233 | 40.8723 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1