Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Bengali
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use Rakib/whisper-tiny-bn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rakib/whisper-tiny-bn with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Rakib/whisper-tiny-bn")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Rakib/whisper-tiny-bn") model = AutoModelForSpeechSeq2Seq.from_pretrained("Rakib/whisper-tiny-bn", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 4.78, | |
| "eval_loss": 0.23136980831623077, | |
| "eval_runtime": 932.4007, | |
| "eval_samples_per_second": 8.959, | |
| "eval_steps_per_second": 1.121, | |
| "eval_wer": 32.89771261927907 | |
| } |