You can deploy this model and start earning money today!

panlr/
hifigan_teochew

Name: hifigan_teochew
Availability: InStock

apache-2.0

Views

No views yet

HiFi-GAN Vocoder for Teochew TTS

模型简介 (Model Description)

本模型是基于 HiFi-GAN 架构训练的潮州话语音合成声码器，用于从梅尔频谱重建高质量音频波形。模型基于 NVIDIA DeepLearningExamples 的训练代码从头开始训练。

(This is a HiFi-GAN vocoder trained for Teochew speech synthesis, designed to reconstruct high-quality audio waveforms from mel-spectrograms. The model was trained from scratch using NVIDIA's DeepLearningExamples training code.)

训练数据 (Training Data)

数据集 (Dataset): teochew-extLa
筛选标准 (Filter Criteria): DNSMOS OVRL > 2.8
数据量 (Data Size): 约 283,000 条音频 (~283,000 audio clips)
总时长 (Total Duration): 555+ 小时 (hours)

训练配置 (Training Configuration)

硬件环境 (Hardware):

双 GPU 训练 (Dual GPU training)
Batch Size: 64
Gradient Accumulation: 4

超参数 (Hyperparameters):

Epochs: 400
Learning Rate: 0.0003
Learning Rate Decay: 0.9998

训练时长 (Training Duration): 约 8 天 (~8 days)

模型架构 (Model Architecture)

生成器配置 (Generator Config):

python

{
    "upsample_rates": [8, 8, 2, 2],
    "upsample_kernel_sizes": [16, 16, 4, 4],
    "upsample_initial_channel": 512,
    "resblock": "1",
    "resblock_kernel_sizes": [3, 7, 11],
    "resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
}

梅尔频谱配置 (Mel-Spectrogram Config):

python

{
    "sampling_rate": 22050,
    "filter_length": 1024,
    "num_mels": 80,
    "hop_length": 256,
    "win_length": 1024,
    "mel_fmin": 0.0,
    "mel_fmax": 11025.0,
    "max_wav_value": 32768.0
}

使用方法 (Usage)

1. 命令行界面 (Command Line Interface)

bash

cd hifigan_standalone
python hifigan_api.py --checkpoint path/to/ckpt.pt --input audio.wav --output out.wav

2. 作为 Python 包导入 (Python Package Import)

python

# 将 hifigan_standalone 所在目录加入 PYTHONPATH，或者放到项目中
# Add hifigan_standalone directory to PYTHONPATH or place it in your project
from hifigan_standalone import HiFiGANVocoder

vocoder = HiFiGANVocoder("path/to/checkpoint.pt")
vocoder.reconstruct_wav("input.wav", "output.wav")

3. 在 Gradio / HuggingFace Space 中使用 (Use with Gradio / HuggingFace Space)

python

import gradio as gr
from hifigan_standalone import HiFiGANVocoder

vocoder = HiFiGANVocoder("ckpt.pt")
demo = gr.Interface(
    fn=vocoder.gradio_reconstruct,
    inputs=gr.Audio(),
    outputs=gr.Audio()
)
demo.launch()

评估结果 (Evaluation Results)

使用 DNSMOS 指标对不同检查点进行评估 (DNSMOS metrics for different checkpoints):

Checkpoint	SIG	BAK	OVRL	Notes
Ground Truth	3.4699	3.8607	3.1040	-
Epoch 100	3.4416	3.7775	3.0382	-
Epoch 210	3.4737	3.7889	3.0724	Best
Epoch 300	3.4232	3.7777	3.0250	Sounds better than the Epoch 210.
Epoch 400	3.3923	3.7841	3.0050	过拟合 (Overfitting)

推荐使用 (Recommended): Checkpoint 210（Epoch 210） or Checkpoint 300（Epoch 300）.

panlr/hifigan_teochew

HiFi-GAN Vocoder for Teochew TTS

模型简介 (Model Description)

训练数据 (Training Data)

训练配置 (Training Configuration)

模型架构 (Model Architecture)

使用方法 (Usage)

1. 命令行界面 (Command Line Interface)

2. 作为 Python 包导入 (Python Package Import)

3. 在 Gradio / HuggingFace Space 中使用 (Use with Gradio / HuggingFace Space)

评估结果 (Evaluation Results)

panlr/
hifigan_teochew