Spaces:
Paused
Paused
File size: 3,315 Bytes
d66c48f |
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 |
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import os
from huggingface_hub import snapshot_download
from models.vc.vevo.vevo_utils import *
def vevo_style(content_wav_path, style_wav_path, output_path):
gen_audio = inference_pipeline.inference_ar_and_fm(
src_wav_path=content_wav_path,
src_text=None,
style_ref_wav_path=style_wav_path,
timbre_ref_wav_path=content_wav_path,
)
save_audio(gen_audio, output_path=output_path)
if __name__ == "__main__":
# ===== Device =====
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
# ===== Content Tokenizer =====
local_dir = snapshot_download(
repo_id="amphion/Vevo",
repo_type="model",
cache_dir="./ckpts/Vevo",
allow_patterns=["tokenizer/vq32/*"],
)
content_tokenizer_ckpt_path = os.path.join(
local_dir, "tokenizer/vq32/hubert_large_l18_c32.pkl"
)
# ===== Content-Style Tokenizer =====
local_dir = snapshot_download(
repo_id="amphion/Vevo",
repo_type="model",
cache_dir="./ckpts/Vevo",
allow_patterns=["tokenizer/vq8192/*"],
)
content_style_tokenizer_ckpt_path = os.path.join(local_dir, "tokenizer/vq8192")
# ===== Autoregressive Transformer =====
local_dir = snapshot_download(
repo_id="amphion/Vevo",
repo_type="model",
cache_dir="./ckpts/Vevo",
allow_patterns=["contentstyle_modeling/Vq32ToVq8192/*"],
)
ar_cfg_path = "./models/vc/vevo/config/Vq32ToVq8192.json"
ar_ckpt_path = os.path.join(local_dir, "contentstyle_modeling/Vq32ToVq8192")
# ===== Flow Matching Transformer =====
local_dir = snapshot_download(
repo_id="amphion/Vevo",
repo_type="model",
cache_dir="./ckpts/Vevo",
allow_patterns=["acoustic_modeling/Vq8192ToMels/*"],
)
fmt_cfg_path = "./models/vc/vevo/config/Vq8192ToMels.json"
fmt_ckpt_path = os.path.join(local_dir, "acoustic_modeling/Vq8192ToMels")
# ===== Vocoder =====
local_dir = snapshot_download(
repo_id="amphion/Vevo",
repo_type="model",
cache_dir="./ckpts/Vevo",
allow_patterns=["acoustic_modeling/Vocoder/*"],
)
vocoder_cfg_path = "./models/vc/vevo/config/Vocoder.json"
vocoder_ckpt_path = os.path.join(local_dir, "acoustic_modeling/Vocoder")
# ===== Inference =====
inference_pipeline = VevoInferencePipeline(
content_tokenizer_ckpt_path=content_tokenizer_ckpt_path,
content_style_tokenizer_ckpt_path=content_style_tokenizer_ckpt_path,
ar_cfg_path=ar_cfg_path,
ar_ckpt_path=ar_ckpt_path,
fmt_cfg_path=fmt_cfg_path,
fmt_ckpt_path=fmt_ckpt_path,
vocoder_cfg_path=vocoder_cfg_path,
vocoder_ckpt_path=vocoder_ckpt_path,
device=device,
)
content_wav_path = "./models/vc/vevo/wav/source.wav"
reference_wav_path = "./models/vc/vevo/wav/arabic_male.wav"
output_path = "./models/vc/vevo/wav/output_vevostyle.wav"
vevo_style(content_wav_path, reference_wav_path, output_path)
|