How to save my output with python?

[TheStalke]

This is literally the python usage example code in README file and I tried to add the get_writer function to save the output but I wasn't able to, can someone tell me what am I doing wrong

def whisper_transcribe(audio_path):
    model = whisper.load_model("tiny")

    audio = whisper.load_audio(audio_path)
    audio = whisper.pad_or_trim(audio)

    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    probs = model.detect_language(mel)
    print(f"Detected language: {max(probs, key=probs.get)}")

    options = whisper.DecodingOptions()
    result = whisper.decode(model, mel, options)

    output = get_writer(filepath, './')
    output(results,  'transcribe.txt')

    return output

[ellkrauze]

Hello, here's the example of using get_writer with result extracted from model.transcribe! Hope, it helps

import whisper
from whisper.utils import get_writer

def whisper_transcribe(
    audio_path: str, 
    model_name: str='tiny',
    output_format: str='json',
    output_dir: str='./',
):
    model = whisper.load_model(model_name)
    language = "en" if model_name.endswith(".en") else None
    result = model.transcribe(
        audio_path, language=language, temperature=0.0, word_timestamps=True
    )

    output = get_writer(output_format=output_format, output_dir=output_dir)
    output(result,  audio_path=audio_path)

It saves the transcripted audio file in JSON in the current directory. However, you can specify other formats: txt, vtt, srt, tsv, json, or all

[TheStalke]

Thank you it does work, sry I forgot to reply on time 🙏🌹