Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

remove 3rd paty wavernn support from server.py and add ModelManager arguments

This commit is contained in:
Eren Gölge 2021-01-21 15:30:16 +01:00
parent 6b6e989fd2
commit 007a4d7139
2 changed files with 25 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
TTS/server/conf.json
View File

@ -5,10 +5,6 @@
"tts_speakers": null, // json file listing speaker ids. null if no speaker embedding.
"vocoder_config":null,
"vocoder_file": null,
"wavernn_lib_path": null, // Rootpath to wavernn project folder to be imported. If this is null, model uses GL for speech synthesis.
"wavernn_path":null, // wavernn model root path
"wavernn_file":null, // wavernn checkpoint file name
"wavernn_config": null, // wavernn config file
"is_wavernn_batched":true,
"port": 5002,
"use_cuda": true,

40
TTS/server/server.py
View File

@ -1,9 +1,12 @@
#!flask/bin/python
import argparse
import os
import sys
from pathlib import Path
from flask import Flask, request, render_template, send_file
from flask import Flask, render_template, request, send_file
from TTS.server.synthesizer import Synthesizer
from TTS.utils.manage import ModelManager
def create_argparser():
@ -11,21 +14,19 @@ def create_argparser():
return x.lower() in ['true', '1', 'yes']
parser = argparse.ArgumentParser()
parser.add_argument('--tts_checkpoint', type=str, help='path to TTS checkpoint file')
parser.add_argument('--tts_config', type=str, help='path to TTS config.json file')
parser.add_argument('--list_models', type=convert_boolean, nargs='?', const=True, default=False, help='list available pre-trained tts and vocoder models.')
parser.add_argument('--model_name', type=str, help='name of one of the released tts models.')
parser.add_argument('--vocoder_name', type=str, help='name of one of the released vocoder models.')
parser.add_argument('--tts_checkpoint', type=str, help='path to custom tts checkpoint file')
parser.add_argument('--tts_config', type=str, help='path to custom tts config.json file')
parser.add_argument('--tts_speakers', type=str, help='path to JSON file containing speaker ids, if speaker ids are used in the model')
parser.add_argument('--wavernn_lib_path', type=str, default=None, help='path to WaveRNN project folder to be imported. If this is not passed, model uses Griffin-Lim for synthesis.')
parser.add_argument('--wavernn_checkpoint', type=str, default=None, help='path to WaveRNN checkpoint file.')
parser.add_argument('--wavernn_config', type=str, default=None, help='path to WaveRNN config file.')
parser.add_argument('--is_wavernn_batched', type=convert_boolean, default=False, help='true to use batched WaveRNN.')
parser.add_argument('--vocoder_config', type=str, default=None, help='path to TTS.vocoder config file.')
parser.add_argument('--vocoder_checkpoint', type=str, default=None, help='path to TTS.vocoder checkpoint file.')
parser.add_argument('--vocoder_config', type=str, default=None, help='path to vocoder config file.')
parser.add_argument('--vocoder_checkpoint', type=str, default=None, help='path to vocoder checkpoint file.')
parser.add_argument('--port', type=int, default=5002, help='port to listen on.')
parser.add_argument('--use_cuda', type=convert_boolean, default=False, help='true to use CUDA.')
parser.add_argument('--debug', type=convert_boolean, default=False, help='true to enable Flask debug mode.')
return parser
synthesizer = None
embedded_models_folder = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'model')
@ -45,6 +46,20 @@ wavernn_config_file = os.path.join(embedded_wavernn_folder, 'config.json')
args = create_argparser().parse_args()
path = Path(__file__).parent / "../../.models.json"
manager = ModelManager(path)
if args.list_models:
manager.list_models()
sys.exit()
# set models by the released models
if args.model_name is not None:
tts_checkpoint_file, tts_config_file = manager.download_model(args.model_name)
if args.vocoder_name is not None:
vocoder_checkpoint_file, vocoder_config_file = manager.download_model(args.vocoder_name)
# If these were not specified in the CLI args, use default values with embedded model files
if not args.tts_checkpoint and os.path.isfile(tts_checkpoint_file):
args.tts_checkpoint = tts_checkpoint_file
@ -56,11 +71,6 @@ if not args.vocoder_checkpoint and os.path.isfile(vocoder_checkpoint_file):
if not args.vocoder_config and os.path.isfile(vocoder_config_file):
args.vocoder_config = vocoder_config_file
if not args.wavernn_checkpoint and os.path.isfile(wavernn_checkpoint_file):
args.wavernn_checkpoint = wavernn_checkpoint_file
if not args.wavernn_config and os.path.isfile(wavernn_config_file):
args.wavernn_config = wavernn_config_file
synthesizer = Synthesizer(args)
app = Flask(__name__)