Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix VCTK recipe and formatter

This commit is contained in:
Eren Gölge 2022-03-08 14:20:14 +01:00
parent 0cf3265a46
commit c670365507
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
TTS/tts/datasets/formatters.py
View File

@ -328,7 +328,7 @@ def vctk(root_path, meta_files=None, wavs_path="wav48_silence_trimmed", mic="mic
else: else:
wav_file = os.path.join(root_path, wavs_path, speaker_id, file_id + f"_{mic}.{file_ext}") wav_file = os.path.join(root_path, wavs_path, speaker_id, file_id + f"_{mic}.{file_ext}")
if os.path.exists(wav_file): if os.path.exists(wav_file):
items.append([text, wav_file, "VCTK_" + speaker_id]) items.append({"text": text, "audio_file": wav_file, "speaker_name": "VCTK_" + speaker_id})
else: else:
print(f" [!] wav files don't exist - {wav_file}") print(f" [!] wav files don't exist - {wav_file}")
return items return items
@ -348,7 +348,7 @@ def vctk_old(root_path, meta_files=None, wavs_path="wav48"):
with open(meta_file, "r", encoding="utf-8") as file_text: with open(meta_file, "r", encoding="utf-8") as file_text:
text = file_text.readlines()[0] text = file_text.readlines()[0]
wav_file = os.path.join(root_path, wavs_path, speaker_id, file_id + ".wav") wav_file = os.path.join(root_path, wavs_path, speaker_id, file_id + ".wav")
items.append([text, wav_file, "VCTK_old_" + speaker_id]) items.append({"text": text, "audio_file": wav_file, "speaker_name": "VCTK_old_" + speaker_id})
return items return items

1
recipes/vctk/vits/train_vits.py
View File

@ -53,6 +53,7 @@ config = VitsConfig(
epochs=1000, epochs=1000,
text_cleaner="english_cleaners", text_cleaner="english_cleaners",
use_phonemes=True, use_phonemes=True,
phoneme_language="en",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"), phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
compute_input_seq_cache=True, compute_input_seq_cache=True,
print_step=25, print_step=25,