Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use michaelszhu/whisper-small-finetuned-radio-ASR-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use michaelszhu/whisper-small-finetuned-radio-ASR-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="michaelszhu/whisper-small-finetuned-radio-ASR-2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("michaelszhu/whisper-small-finetuned-radio-ASR-2") model = AutoModelForSpeechSeq2Seq.from_pretrained("michaelszhu/whisper-small-finetuned-radio-ASR-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Radio modification
#1
by PreethaVitra - opened
Hi,
Than k you for your work. Could you explain how you did the radio modification of the Common Voice data
Hello - we applied a band pass filter and randomly added white noise to simulate a lower audio quality that would be present in radio audio.