-
-
Save Xsir0/2199c4e220531f0382824c629568213e to your computer and use it in GitHub Desktop.
mlx-whisper real time audio
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Required packages: | |
| # pip install SpeechRecognition mlx-whisper pyaudio | |
| # Note: This script requires Apple Silicon Mac for MLX Whisper | |
| import speech_recognition as sr | |
| import numpy as np | |
| import mlx_whisper | |
| r = sr.Recognizer() | |
| mic = sr.Microphone(sample_rate=16000) | |
| print("Listening...") | |
| try: | |
| with mic as source: | |
| r.adjust_for_ambient_noise(source) | |
| while True: | |
| audio = r.listen(source) | |
| # Convert audio to numpy array | |
| audio_data = np.frombuffer(audio.get_raw_data(), dtype=np.int16).astype(np.float32) / 32768.0 | |
| # Process audio with Apple MLXWhisper model | |
| result = mlx_whisper.transcribe(audio_data, path_or_hf_repo="mlx-community/whisper-large-v3-turbo")["text"] | |
| # Print the transcribed text | |
| print(result) | |
| except KeyboardInterrupt: | |
| print("Stopped listening.") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment