mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-16 20:52:08 -04:00
Signed-off-by: Andreas Egli <github@kharan.ch> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
125 lines
4.5 KiB
Python
Executable File
125 lines
4.5 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
This is an extra gRPC server of LocalAI for Faster Whisper 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 faster_whisper import WhisperModel
|
|
|
|
import grpc
|
|
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
|
|
sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
|
|
from grpc_auth import get_auth_interceptors
|
|
|
|
|
|
|
|
_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):
|
|
device = "cpu"
|
|
# Get device
|
|
# device = "cuda" if request.CUDA else "cpu"
|
|
if request.CUDA:
|
|
device = "cuda"
|
|
mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
|
|
if mps_available:
|
|
device = "mps"
|
|
try:
|
|
print("Preparing models, please wait", file=sys.stderr)
|
|
self.model = WhisperModel(request.Model, device=device, compute_type="default")
|
|
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 AudioTranscription(self, request, context):
|
|
resultSegments = []
|
|
text = ""
|
|
try:
|
|
word_timestamps = "word" in request.timestamp_granularities
|
|
segments, info = self.model.transcribe(request.dst, beam_size=5, condition_on_previous_text=False, word_timestamps=word_timestamps)
|
|
id = 0
|
|
for segment in segments:
|
|
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
|
|
words = []
|
|
if word_timestamps and hasattr(segment, 'words'):
|
|
for word in segment.words:
|
|
words.append(backend_pb2.TranscriptWord(
|
|
start=int(word.start * 1e9),
|
|
end=int(word.end * 1e9),
|
|
text=word.word
|
|
))
|
|
|
|
resultSegments.append(backend_pb2.TranscriptSegment(
|
|
id=id,
|
|
start=int(segment.start * 1e9),
|
|
end=int(segment.end * 1e9),
|
|
text=segment.text,
|
|
words=words
|
|
))
|
|
text += segment.text
|
|
id += 1
|
|
except Exception as err:
|
|
print(f"Unexpected {err=}, {type(err)=}", file=sys.stderr)
|
|
raise err
|
|
|
|
return backend_pb2.TranscriptResult(segments=resultSegments, text=text)
|
|
|
|
def serve(address):
|
|
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
|
|
options=[
|
|
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
|
|
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
|
|
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
|
|
],
|
|
interceptors=get_auth_interceptors(),
|
|
)
|
|
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)
|