metadata
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
- hf-asr-leaderboard
- pashto
- ps
datasets:
- google/fleurs
metrics:
- wer
base_model: openai/whisper-medium
model-index:
- name: Whisper Medium Pashto
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: google/fleurs
type: google/fleurs
args: 'config: ps_af, split: test'
metrics:
- type: wer
value: 49.4855
name: Wer
Whisper Medium Pashto
This model is a fine-tuned version of openai/whisper-medium on the google/fleurs ps_af dataset. It achieves the following results on the evaluation set:
- Loss: 1.4807
- Wer: 50.5448
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: 3e-07
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 1200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0334 | 14.29 | 100 | 1.0348 | 50.0908 |
| 0.0021 | 28.57 | 200 | 1.1971 | 49.4855 |
| 0.0007 | 42.86 | 300 | 1.2651 | 49.7352 |
| 0.0006 | 57.14 | 400 | 1.3084 | 49.9697 |
| 0.0005 | 71.43 | 500 | 1.3479 | 50.0605 |
| 0.0004 | 85.71 | 600 | 1.3835 | 50.3027 |
| 0.0004 | 100.0 | 700 | 1.4139 | 50.4540 |
| 0.0004 | 114.29 | 800 | 1.4382 | 50.4616 |
| 0.0004 | 128.57 | 900 | 1.4545 | 50.5297 |
| 0.0003 | 142.86 | 1000 | 1.4603 | 50.5675 |
| 0.0003 | 157.14 | 1100 | 1.4750 | 50.5599 |
| 0.0003 | 171.43 | 1200 | 1.4807 | 50.5448 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2