Created
April 14, 2024 17:31
-
-
Save AIWintermuteAI/0de9f7ba1bd2a7313157c9ccd43ec1d6 to your computer and use it in GitHub Desktop.
Barebone single-threaded implementation of FasterWhisper transcription from the microphone
This file contains 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
| import pyaudio | |
| import numpy as np | |
| CHUNK_SIZE = 16000 * 5 | |
| FORMAT = pyaudio.paInt16 | |
| CHANNELS = 1 | |
| RATE = 16000 | |
| from faster_whisper import WhisperModel | |
| model_size = "tiny.en" | |
| def send_audio(): | |
| p = pyaudio.PyAudio() | |
| stream = p.open(format=FORMAT, | |
| channels=CHANNELS, | |
| rate=RATE, | |
| input=True, | |
| frames_per_buffer=CHUNK_SIZE) | |
| model = WhisperModel(model_size, device="cpu", compute_type="int8") | |
| try: | |
| while True: | |
| data = stream.read(CHUNK_SIZE) | |
| numpy_data = np.frombuffer(data, dtype = np.float32) | |
| numpy_data = numpy_data.astype(np.float32) / 32768.0 | |
| segments, info = model.transcribe(numpy_data, beam_size=5, language="en") | |
| for segment in segments: | |
| print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text)) | |
| except KeyboardInterrupt: | |
| print("Stopping...") | |
| finally: | |
| stream.stop_stream() | |
| stream.close() | |
| p.terminate() | |
| if __name__ == '__main__': | |
| send_audio() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment