Initial commit

configs/data/ljspeech.yaml

@@ -0,0 +1,21 @@
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: ljspeech
+train_filelist_path: data/filelists/ljs_audio_text_train_filelist.txt
+valid_filelist_path: data/filelists/ljs_audio_text_val_filelist.txt
+batch_size: 32
+num_workers: 20
+pin_memory: True
+cleaners: [english_cleaners2]
+add_blank: True
+n_spks: 1
+n_fft: 1024
+n_feats: 80
+sample_rate: 22050
+hop_length: 256
+win_length: 1024
+f_min: 0
+f_max: 8000
+data_statistics:  # Computed for ljspeech dataset
+  mel_mean: -5.536622
+  mel_std: 2.116101
+seed: ${seed}

configs/data/vctk.yaml

@@ -0,0 +1,14 @@
+defaults:
+  - ljspeech
+  - _self_
+
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: vctk
+train_filelist_path: data/filelists/vctk_audio_sid_text_train_filelist.txt
+valid_filelist_path: data/filelists/vctk_audio_sid_text_val_filelist.txt
+batch_size: 32
+add_blank: True
+n_spks: 109
+data_statistics:  # Computed for vctk dataset
+  mel_mean: -6.630575
+  mel_std: 2.482914