Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Persian
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("zahrakh98/check_points")
model = AutoModelForSpeechSeq2Seq.from_pretrained("zahrakh98/check_points")Quick Links
Whisper Small fa
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5556
- Wer: 59.0415
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: 600
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9736 | 0.09 | 200 | 1.1516 | 69.9194 |
| 0.3892 | 0.17 | 400 | 0.6260 | 61.1574 |
| 0.3177 | 0.26 | 600 | 0.5556 | 59.0415 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 4
Model tree for zahrakh98/check_points
Base model
openai/whisper-smallSpace using zahrakh98/check_points 1
Evaluation results
- Wer on Common Voice 11.0test set self-reported59.042
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="zahrakh98/check_points")