from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

# Load model and processor
processor = WhisperProcessor.from_pretrained("AfroLogicInsect/whisper-finetuned-float32")
model = WhisperForConditionalGeneration.from_pretrained("AfroLogicInsect/whisper-finetuned-float32")

# Load audio
audio, sr = librosa.load("path/to/audio.wav", sr=16000)

# Process
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features

# Generate transcription
with torch.no_grad():
    predicted_ids = model.generate(input_features)
    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]

print(transcription)

Training Details

Base Model: OpenAI Whisper
Training Dataset: [Add your dataset details]
Training Parameters: [Add your training parameters]
Evaluation Metrics: [Add your evaluation results]

Limitations and Biases

This model may have biases present in the training data
Performance may vary on different accents or audio qualities
Recommended for English speech recognition tasks

Citation

If you use this model, please cite:

bibtex

@misc{whisper-finetuned,
  author = {Daniel AMAH},
  title = {Fine-tuned Whisper Model},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/AfroLogicInsect/whisper-finetuned-float32}
}