78 lines
2.2 KiB
Python
78 lines
2.2 KiB
Python
# coding=utf-8
|
|
# Copyright 2026 The Alibaba Qwen team.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
# 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.
|
|
import time
|
|
import torch
|
|
import soundfile as sf
|
|
|
|
from qwen_tts import Qwen3TTSModel
|
|
|
|
|
|
def main():
|
|
device = "cuda:0"
|
|
MODEL_PATH = "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice/"
|
|
|
|
tts = Qwen3TTSModel.from_pretrained(
|
|
MODEL_PATH,
|
|
device_map=device,
|
|
dtype=torch.bfloat16,
|
|
attn_implementation="flash_attention_2",
|
|
)
|
|
|
|
# -------- Single (with instruct) --------
|
|
torch.cuda.synchronize()
|
|
t0 = time.time()
|
|
|
|
wavs, sr = tts.generate_custom_voice(
|
|
text="其实我真的有发现，我是一个特别善于观察别人情绪的人。",
|
|
language="Chinese",
|
|
speaker="Vivian",
|
|
instruct="用特别愤怒的语气说",
|
|
)
|
|
|
|
torch.cuda.synchronize()
|
|
t1 = time.time()
|
|
print(f"[CustomVoice Single] time: {t1 - t0:.3f}s")
|
|
|
|
sf.write("qwen3_tts_test_custom_single.wav", wavs[0], sr)
|
|
|
|
# -------- Batch (some empty instruct) --------
|
|
texts = ["其实我真的有发现，我是一个特别善于观察别人情绪的人。", "She said she would be here by noon."]
|
|
languages = ["Chinese", "English"]
|
|
speakers = ["Vivian", "Ryan"]
|
|
instructs = ["", "Very happy."]
|
|
|
|
torch.cuda.synchronize()
|
|
t0 = time.time()
|
|
|
|
wavs, sr = tts.generate_custom_voice(
|
|
text=texts,
|
|
language=languages,
|
|
speaker=speakers,
|
|
instruct=instructs,
|
|
max_new_tokens=2048,
|
|
)
|
|
|
|
torch.cuda.synchronize()
|
|
t1 = time.time()
|
|
print(f"[CustomVoice Batch] time: {t1 - t0:.3f}s")
|
|
|
|
for i, w in enumerate(wavs):
|
|
sf.write(f"qwen3_tts_test_custom_batch_{i}.wav", w, sr)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|