mirror of
https://github.com/davesarmoury/GLaDOS.git
synced 2025-11-04 14:49:45 +08:00
50 lines
1.3 KiB
YAML
50 lines
1.3 KiB
YAML
name: "ds_for_fastpitch_align"
|
|
|
|
manifest_filepath: "train_manifest.json"
|
|
sup_data_path: "sup_data"
|
|
sup_data_types: [ "align_prior_matrix", "pitch" ]
|
|
phoneme_dict_path: "scripts/tts_dataset_files/cmudict-0.7b_nv22.10"
|
|
heteronyms_path: "scripts/tts_dataset_files/heteronyms-052722"
|
|
|
|
dataset:
|
|
_target_: nemo.collections.tts.data.dataset.TTSDataset
|
|
manifest_filepath: ${manifest_filepath}
|
|
sample_rate: 22050
|
|
sup_data_path: ${sup_data_path}
|
|
sup_data_types: ${sup_data_types}
|
|
n_fft: 1024
|
|
win_length: 1024
|
|
hop_length: 256
|
|
window: "hann"
|
|
n_mels: 80
|
|
lowfreq: 0
|
|
highfreq: 8000
|
|
max_duration: null
|
|
min_duration: 0.1
|
|
ignore_file: null
|
|
trim: false
|
|
pitch_fmin: 65.40639132514966
|
|
pitch_fmax: 2093.004522404789
|
|
|
|
text_normalizer:
|
|
_target_: nemo_text_processing.text_normalization.normalize.Normalizer
|
|
lang: en
|
|
input_case: cased
|
|
|
|
text_normalizer_call_kwargs:
|
|
verbose: false
|
|
punct_pre_process: true
|
|
punct_post_process: true
|
|
|
|
text_tokenizer:
|
|
_target_: nemo.collections.common.tokenizers.text_to_speech.tts_tokenizers.EnglishPhonemesTokenizer
|
|
punct: true
|
|
stresses: true
|
|
chars: true
|
|
apostrophe: true
|
|
pad_with_space: true
|
|
g2p:
|
|
_target_: nemo.collections.tts.g2p.models.en_us_arpabet.EnglishG2p
|
|
phoneme_dict: ${phoneme_dict_path}
|
|
heteronyms: ${heteronyms_path}
|