Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Oriya
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("auro/whisper-cli-small-or")
model = AutoModelForSpeechSeq2Seq.from_pretrained("auro/whisper-cli-small-or")Quick Links
Whisper Small Odia
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 or dataset. It achieves the following results on the evaluation set:
- Loss: 0.4245
- Wer: 27.0240
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: 32
- eval_batch_size: 32
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0021 | 49.0 | 1000 | 0.4245 | 27.0240 |
| 0.0001 | 99.0 | 2000 | 0.7338 | 28.1241 |
| 0.0 | 149.0 | 3000 | 0.8594 | 28.6601 |
| 0.0 | 199.0 | 4000 | 0.9103 | 28.3498 |
| 0.0 | 249.0 | 5000 | 0.9329 | 28.2934 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 7
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 ortest set self-reported27.024
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="auro/whisper-cli-small-or")