audio_to_text.py

from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torchaudio


# load model and processor
processor = WhisperProcessor.from_pretrained("openai/whisper-tiny")
model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny")
model.config.forced_decoder_ids = None


def audio_to_text(audio_data):
    # Convert raw audio frame (numpy array) to tensor and resample it to 16 kHz
    waveform = torch.tensor(audio_data, dtype=torch.float32).unsqueeze(0)
    # Check if the sample rate is 16 kHz; if not, resample it
    if sample_rate != 16000:
        resampler = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)
        waveform = resampler(waveform)
    waveform = waveform.squeeze().numpy()
    input_features = processor(waveform, sampling_rate=16000, return_tensors="pt").input_features

    # generate token ids
    predicted_ids = model.generate(input_features)
    # decode token ids to text
    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
    return transcription