File size: 4,595 Bytes
7def60a |
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 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
#!/usr/bin/env python3
"""
This is an extra gRPC server of LocalAI for Bark TTS
"""
from concurrent import futures
import time
import argparse
import signal
import sys
import os
import backend_pb2
import backend_pb2_grpc
import torch
from TTS.api import TTS
import grpc
_ONE_DAY_IN_SECONDS = 60 * 60 * 24
# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
COQUI_LANGUAGE = os.environ.get('COQUI_LANGUAGE', None)
# Implement the BackendServicer class with the service methods
class BackendServicer(backend_pb2_grpc.BackendServicer):
"""
BackendServicer is the class that implements the gRPC service
"""
def Health(self, request, context):
return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
def LoadModel(self, request, context):
# Get device
# device = "cuda" if request.CUDA else "cpu"
if torch.cuda.is_available():
print("CUDA is available", file=sys.stderr)
device = "cuda"
else:
print("CUDA is not available", file=sys.stderr)
device = "cpu"
if not torch.cuda.is_available() and request.CUDA:
return backend_pb2.Result(success=False, message="CUDA is not available")
self.AudioPath = None
# List available 🐸TTS models
print(TTS().list_models())
if os.path.isabs(request.AudioPath):
self.AudioPath = request.AudioPath
elif request.AudioPath and request.ModelFile != "" and not os.path.isabs(request.AudioPath):
# get base path of modelFile
modelFileBase = os.path.dirname(request.ModelFile)
# modify LoraAdapter to be relative to modelFileBase
self.AudioPath = os.path.join(modelFileBase, request.AudioPath)
try:
print("Preparing models, please wait", file=sys.stderr)
self.tts = TTS(request.Model).to(device)
except Exception as err:
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
# Implement your logic here for the LoadModel service
# Replace this with your desired response
return backend_pb2.Result(message="Model loaded successfully", success=True)
def TTS(self, request, context):
try:
# if model is multilangual add language from request or env as fallback
lang = request.language or COQUI_LANGUAGE
if lang == "":
lang = None
if self.tts.is_multi_lingual and lang is None:
return backend_pb2.Result(success=False, message=f"Model is multi-lingual, but no language was provided")
# if model is multi-speaker, use speaker_wav or the speaker_id from request.voice
if self.tts.is_multi_speaker and self.AudioPath is None and request.voice is None:
return backend_pb2.Result(success=False, message=f"Model is multi-speaker, but no speaker was provided")
if self.tts.is_multi_speaker and request.voice is not None:
self.tts.tts_to_file(text=request.text, speaker=request.voice, language=lang, file_path=request.dst)
else:
self.tts.tts_to_file(text=request.text, speaker_wav=self.AudioPath, language=lang, file_path=request.dst)
except Exception as err:
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
return backend_pb2.Result(success=True)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()
print("Server started. Listening on: " + address, file=sys.stderr)
# Define the signal handler function
def signal_handler(sig, frame):
print("Received termination signal. Shutting down...")
server.stop(0)
sys.exit(0)
# Set the signal handlers for SIGINT and SIGTERM
signal.signal(signal.SIGINT, signal_handler)
signal.signal(signal.SIGTERM, signal_handler)
try:
while True:
time.sleep(_ONE_DAY_IN_SECONDS)
except KeyboardInterrupt:
server.stop(0)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Run the gRPC server.")
parser.add_argument(
"--addr", default="localhost:50051", help="The address to bind the server to."
)
args = parser.parse_args()
serve(args.addr)
|