Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Indonesian
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("TheRains/output")
model = AutoModelForSpeechSeq2Seq.from_pretrained("TheRains/output")Quick Links
Whisper small ID - Augmented
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_12_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1483
- Wer: 5.6978
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3979 | 0.77 | 200 | 0.2141 | 9.7635 |
| 0.2625 | 1.54 | 400 | 0.1705 | 7.3636 |
| 0.1398 | 2.31 | 600 | 0.1551 | 6.9636 |
| 0.0666 | 3.07 | 800 | 0.1678 | 6.2043 |
| 0.0411 | 3.84 | 1000 | 0.1483 | 5.6978 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 15
Evaluation results
- Wer on mozilla-foundation/common_voice_12_0test set self-reported5.698
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="TheRains/output")