File size: 3,264 Bytes
8ad4e11 |
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 |
# Copyright (c) 2024 Alibaba Inc (authors: Xiang Lyu)
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import print_function
import argparse
import logging
logging.getLogger('matplotlib').setLevel(logging.WARNING)
import os
import sys
import torch
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.append('{}/../..'.format(ROOT_DIR))
sys.path.append('{}/../../third_party/Matcha-TTS'.format(ROOT_DIR))
from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
def get_args():
parser = argparse.ArgumentParser(description='export your model for deployment')
parser.add_argument('--model_dir',
type=str,
default='pretrained_models/CosyVoice-300M',
help='local path')
args = parser.parse_args()
print(args)
return args
def get_optimized_script(model, preserved_attrs=[]):
script = torch.jit.script(model)
if preserved_attrs != []:
script = torch.jit.freeze(script, preserved_attrs=preserved_attrs)
else:
script = torch.jit.freeze(script)
script = torch.jit.optimize_for_inference(script)
return script
def main():
args = get_args()
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)s %(message)s')
torch._C._jit_set_fusion_strategy([('STATIC', 1)])
torch._C._jit_set_profiling_mode(False)
torch._C._jit_set_profiling_executor(False)
try:
model = CosyVoice(args.model_dir)
except Exception:
try:
model = CosyVoice2(args.model_dir)
except Exception:
raise TypeError('no valid model_type!')
if not isinstance(model, CosyVoice2):
# 1. export llm text_encoder
llm_text_encoder = model.model.llm.text_encoder
script = get_optimized_script(llm_text_encoder)
script.save('{}/llm.text_encoder.fp32.zip'.format(args.model_dir))
script = get_optimized_script(llm_text_encoder.half())
script.save('{}/llm.text_encoder.fp16.zip'.format(args.model_dir))
# 2. export llm llm
llm_llm = model.model.llm.llm
script = get_optimized_script(llm_llm, ['forward_chunk'])
script.save('{}/llm.llm.fp32.zip'.format(args.model_dir))
script = get_optimized_script(llm_llm.half(), ['forward_chunk'])
script.save('{}/llm.llm.fp16.zip'.format(args.model_dir))
# 3. export flow encoder
flow_encoder = model.model.flow.encoder
script = get_optimized_script(flow_encoder)
script.save('{}/flow.encoder.fp32.zip'.format(args.model_dir))
script = get_optimized_script(flow_encoder.half())
script.save('{}/flow.encoder.fp16.zip'.format(args.model_dir))
if __name__ == '__main__':
main()
|