Hugging Face's logo

Spaces:
Svngoku
/
maskgct-audio-lab
Running on Zero

App Files Community
maskgct-audio-lab
File size: 3,484 Bytes 
c968fc3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# Copyright (c) 2024 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

from models.tts.maskgct.maskgct_utils import *
from huggingface_hub import hf_hub_download
import safetensors
import soundfile as sf

if __name__ == "__main__":

    # build model
    device = torch.device("cuda:0")
    cfg_path = "./models/tts/maskgct/config/maskgct.json"
    cfg = load_config(cfg_path)
    # 1. build semantic model (w2v-bert-2.0)
    semantic_model, semantic_mean, semantic_std = build_semantic_model(device)
    # 2. build semantic codec
    semantic_codec = build_semantic_codec(cfg.model.semantic_codec, device)
    # 3. build acoustic codec
    codec_encoder, codec_decoder = build_acoustic_codec(
        cfg.model.acoustic_codec, device
    )
    # 4. build t2s model
    t2s_model = build_t2s_model(cfg.model.t2s_model, device)
    # 5. build s2a model
    s2a_model_1layer = build_s2a_model(cfg.model.s2a_model.s2a_1layer, device)
    s2a_model_full = build_s2a_model(cfg.model.s2a_model.s2a_full, device)

    # download checkpoint
    # download semantic codec ckpt
    semantic_code_ckpt = hf_hub_download(
        "amphion/MaskGCT", filename="semantic_codec/model.safetensors"
    )
    # download acoustic codec ckpt
    codec_encoder_ckpt = hf_hub_download(
        "amphion/MaskGCT", filename="acoustic_codec/model.safetensors"
    )
    codec_decoder_ckpt = hf_hub_download(
        "amphion/MaskGCT", filename="acoustic_codec/model_1.safetensors"
    )
    # download t2s model ckpt
    t2s_model_ckpt = hf_hub_download(
        "amphion/MaskGCT", filename="t2s_model/model.safetensors"
    )
    # download s2a model ckpt
    s2a_1layer_ckpt = hf_hub_download(
        "amphion/MaskGCT", filename="s2a_model/s2a_model_1layer/model.safetensors"
    )
    s2a_full_ckpt = hf_hub_download(
        "amphion/MaskGCT", filename="s2a_model/s2a_model_full/model.safetensors"
    )

    # load semantic codec
    safetensors.torch.load_model(semantic_codec, semantic_code_ckpt)
    # load acoustic codec
    safetensors.torch.load_model(codec_encoder, codec_encoder_ckpt)
    safetensors.torch.load_model(codec_decoder, codec_decoder_ckpt)
    # load t2s model
    safetensors.torch.load_model(t2s_model, t2s_model_ckpt)
    # load s2a model
    safetensors.torch.load_model(s2a_model_1layer, s2a_1layer_ckpt)
    safetensors.torch.load_model(s2a_model_full, s2a_full_ckpt)

    # inference
    prompt_wav_path = "./models/tts/maskgct/wav/prompt.wav"
    save_path = "[YOUR SAVE PATH]"
    prompt_text = " We do not break. We never give in. We never back down."
    target_text = "In this paper, we introduce MaskGCT, a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision."
    # Specify the target duration (in seconds). If target_len = None, we use a simple rule to predict the target duration.
    target_len = 18
    maskgct_inference_pipeline = MaskGCT_Inference_Pipeline(
        semantic_model,
        semantic_codec,
        codec_encoder,
        codec_decoder,
        t2s_model,
        s2a_model_1layer,
        s2a_model_full,
        semantic_mean,
        semantic_std,
        device,
    )

    recovered_audio = maskgct_inference_pipeline.maskgct_inference(
        prompt_wav_path, prompt_text, target_text, "en", "en", target_len=target_len
    )

    sf.write(save_path, recovered_audio, 24000)