Closed itsupera closed 3 years ago
Hello,
I'm trying to align a Japanese audiobook with the text. My setup:
The alignment is very bad, even when I use a short extract of a few sentences.
I run aeneas like so:
python3 -m aeneas.tools.execute_task \ "extract.mp3" \ "extract.txt" \ "task_language=JA|os_task_file_format=aud|is_text_type=plain" -r="tts=espeak-ng|allow_unlisted_languages=True" \ "extract_markers.txt" \ --output-html
The text has one sentence per line and looks like this:
僕の「自己理解メソッド」を説明する前に、まずは「やりたいこと」探しに関する迷信を解いておきます。 ここで紹介する「5つの間違い」を持ったまま「やりたいこと探し」を進めても、やりたいことは見つかりません。 けれどこの間違いにハマってしまっている人が実に多いのです。 ...
I also tried converting it into kana (ぼくの, ボクノ) or phonemes ([[b o k u ]][[n o ]]), but it does not improve.
ぼくの
ボクノ
[[b o k u ]][[n o ]]
I'm not sure about this, but maybe it could be related to an issue with espeak-ng, see my comment here: https://github.com/espeak-ng/espeak-ng/issues/566#issuecomment-880100908
espeak-ng
Any help would be greatly appreciated, thank you !
The cause for this bad performance was indeed espeak-ng, because after switching the TTS engine to aws everything worked perfectly.
aws
Hello,
I'm trying to align a Japanese audiobook with the text. My setup:
The alignment is very bad, even when I use a short extract of a few sentences.
I run aeneas like so:
The text has one sentence per line and looks like this:
I also tried converting it into kana (
ぼくの
,ボクノ
) or phonemes ([[b o k u ]][[n o ]]
), but it does not improve.I'm not sure about this, but maybe it could be related to an issue with
espeak-ng
, see my comment here: https://github.com/espeak-ng/espeak-ng/issues/566#issuecomment-880100908Any help would be greatly appreciated, thank you !