85 lines
2.9 KiB
Python
85 lines
2.9 KiB
Python
import mlx_whisper
|
|
import numpy as np
|
|
import sounddevice as sd
|
|
import queue
|
|
import sys
|
|
import torch
|
|
from silero_vad import load_silero_vad, get_speech_timestamps
|
|
|
|
# Parameters
|
|
MODEL_PATH = "mlx-community/whisper-small.en-mlx" # MLX optimized small model
|
|
CHANNELS = 1
|
|
SAMPLERATE = 16000
|
|
BLOCK_SIZE = 512 # Silero VAD prefers 512, 1024, or 1536
|
|
VAD_THRESHOLD = 0.5
|
|
BUFFER_LIMIT = SAMPLERATE * 30
|
|
MIN_SILENCE_DURATION_MS = 500
|
|
|
|
audio_queue = queue.Queue()
|
|
|
|
def callback(indata, frames, time, status):
|
|
if status:
|
|
print(status, file=sys.stderr)
|
|
audio_queue.put(indata.copy())
|
|
|
|
def main():
|
|
print(f"Loading MLX-optimized Whisper model '{MODEL_PATH}'...")
|
|
# mlx-whisper uses the same model names or Hugging Face paths
|
|
|
|
print("Loading Silero VAD model...")
|
|
vad_model = load_silero_vad()
|
|
|
|
print("Models loaded.")
|
|
|
|
print("\nStarting live transcription (MLX + VAD)... (Press Ctrl+C to stop)")
|
|
|
|
audio_buffer = []
|
|
speech_started = False
|
|
|
|
try:
|
|
with sd.InputStream(samplerate=SAMPLERATE, channels=CHANNELS, callback=callback, blocksize=BLOCK_SIZE):
|
|
while True:
|
|
while not audio_queue.empty():
|
|
data = audio_queue.get()
|
|
audio_buffer.append(data.flatten())
|
|
|
|
if len(audio_buffer) > 0:
|
|
current_audio = np.concatenate(audio_buffer)
|
|
audio_tensor = torch.from_numpy(current_audio)
|
|
|
|
speech_timestamps = get_speech_timestamps(
|
|
audio_tensor,
|
|
vad_model,
|
|
sampling_rate=SAMPLERATE,
|
|
threshold=VAD_THRESHOLD,
|
|
min_silence_duration_ms=MIN_SILENCE_DURATION_MS
|
|
)
|
|
|
|
if len(speech_timestamps) > 0:
|
|
speech_started = True
|
|
last_end = speech_timestamps[-1]['end']
|
|
buffer_len_samples = len(current_audio)
|
|
|
|
if (buffer_len_samples - last_end) > (SAMPLERATE * MIN_SILENCE_DURATION_MS / 1000) or buffer_len_samples > BUFFER_LIMIT:
|
|
|
|
# Transcribe with MLX
|
|
result = mlx_whisper.transcribe(current_audio, path_or_hf_repo=MODEL_PATH)
|
|
text = result['text'].strip()
|
|
|
|
if text:
|
|
print(f"Transcription: {text}")
|
|
|
|
audio_buffer = []
|
|
speech_started = False
|
|
|
|
elif not speech_started and len(current_audio) > SAMPLERATE * 2:
|
|
audio_buffer = []
|
|
|
|
except KeyboardInterrupt:
|
|
print("\nStopped by user.")
|
|
except Exception as e:
|
|
print(f"\nError: {e}")
|
|
|
|
if __name__ == "__main__":
|
|
main()
|