| 123456789101112131415161718192021222324252627282930 |
- dataset: "AISHELL3"
- path:
- corpus_path: "/app/Choozmo/TTS_fs2/Data/AISHELL-3"
- lexicon_path: "lexicon/pinyin-lexicon-r.txt"
- raw_path: "raw_data/AISHELL3"
- preprocessed_path: "preprocessed_data/AISHELL3"
- preprocessing:
- val_size: 512
- text:
- text_cleaners: []
- language: "zh"
- audio:
- sampling_rate: 22050
- max_wav_value: 32768.0
- stft:
- filter_length: 1024
- hop_length: 256
- win_length: 1024
- mel:
- n_mel_channels: 80
- mel_fmin: 0
- mel_fmax: 8000 # please set to 8000 for HiFi-GAN vocoder, set to null for MelGAN vocoder
- pitch:
- feature: "phoneme_level" # support 'phoneme_level' or 'frame_level'
- normalization: True
- energy:
- feature: "phoneme_level" # support 'phoneme_level' or 'frame_level'
- normalization: True
|
