metadata
language:
- ps
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Medium Pashto - Hassaan Butt
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: google/fleurs
config: ps_af
split: test
args: 'config: ps, split: test'
metrics:
- name: Wer
type: wer
value: 40.46606953089418
Whisper Medium Pashto - Hassaan Butt
This model is a fine-tuned version of openai/whisper-medium on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.9188
- Wer: 40.4661
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: 8
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2231 | 2.92 | 1000 | 0.6001 | 43.4720 |
| 0.0246 | 5.85 | 2000 | 0.7702 | 42.8571 |
| 0.0016 | 8.77 | 3000 | 0.8807 | 41.0354 |
| 0.0004 | 11.7 | 4000 | 0.9188 | 40.4661 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.8.0
- Tokenizers 0.13.2