Spaces:
Running
on
Zero
Running
on
Zero
File size: 2,017 Bytes
1a19e0f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
import socket
import asyncio
import pyaudio
import numpy as np
import logging
import time
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
async def listen_to_F5TTS(text, server_ip="localhost", server_port=9998):
client_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
await asyncio.get_event_loop().run_in_executor(None, client_socket.connect, (server_ip, int(server_port)))
start_time = time.time()
first_chunk_time = None
async def play_audio_stream():
nonlocal first_chunk_time
p = pyaudio.PyAudio()
stream = p.open(format=pyaudio.paFloat32, channels=1, rate=24000, output=True, frames_per_buffer=2048)
try:
while True:
data = await asyncio.get_event_loop().run_in_executor(None, client_socket.recv, 8192)
if not data:
break
if data == b"END":
logger.info("End of audio received.")
break
audio_array = np.frombuffer(data, dtype=np.float32)
stream.write(audio_array.tobytes())
if first_chunk_time is None:
first_chunk_time = time.time()
finally:
stream.stop_stream()
stream.close()
p.terminate()
logger.info(f"Total time taken: {time.time() - start_time:.4f} seconds")
try:
data_to_send = f"{text}".encode("utf-8")
await asyncio.get_event_loop().run_in_executor(None, client_socket.sendall, data_to_send)
await play_audio_stream()
except Exception as e:
logger.error(f"Error in listen_to_F5TTS: {e}")
finally:
client_socket.close()
if __name__ == "__main__":
text_to_send = "As a Reader assistant, I'm familiar with new technology. which are key to its improved performance in terms of both training speed and inference efficiency. Let's break down the components"
asyncio.run(listen_to_F5TTS(text_to_send))
|