Automatic Speech Recognition
Transformers
PyTorch
English
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("Wishwa98/ASRCOMMONACCENT_LessEpoch")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Wishwa98/ASRCOMMONACCENT_LessEpoch")Quick Links
Whisper Small for Common Accent
This model is a fine-tuned version of openai/whisper-small on the Common Accent dataset. It achieves the following results on the evaluation set:
- Loss: 0.3213
- Wer Ortho: 16.2560
- Wer: 11.5126
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.1011 | 1.14 | 500 | 0.3213 | 16.2560 | 11.5126 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 6
Model tree for Wishwa98/ASRCOMMONACCENT_LessEpoch
Base model
openai/whisper-smallDataset used to train Wishwa98/ASRCOMMONACCENT_LessEpoch
Evaluation results
- Wer on Common Accentself-reported11.513
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Wishwa98/ASRCOMMONACCENT_LessEpoch")