You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the bug
PR #5579 broke xvector-conditioned TTS model packaging. In stage 9 of tts.sh, spk_xvector.ark was replaced with {spk_embed_tag}.ark, which in my recipe resolves to xvector.ark. That file does not exist whereas spk_xvector.ark does.
Basic environments:
OS information: Linux 4.18.0-513.18.1.el8_9.x86_64 Updated sphinx documents #1 SMP Wed Feb 21 21:34:36 UTC 2024 x86_64
run any xvector-based recipe up until the model packaging stage (e.g. jtubespeech)
e.g. cd egs2/jtubespeech/tts1; ./run.sh --stop-stage 8
execute ./run.sh --stage 9 --stop-stage 9
Observe command output
To Fix
This error originates in the following lines, and can be fixed by modifying lines 1133 and 1134 of tts.sh, changing {spk_embed_tag}.ark to spk_{spk_embed_tag}.ark and {spk_embed_tag}.scp to spk_{spk_embed_tag}.scp :
I'm not sure whether or how this may affect the new speaker embedding implementation, perhaps the PR author @ftshijt has insight into that?
By the way, thanks for the great work on better integrating speaker embeddings into TTS recipes. I look forward to training an Icelandic speaker embedding model for multi-speaker TTS.
The text was updated successfully, but these errors were encountered:
Thanks for the note! You are correct, the packing should be updated. I will have a check tomorrow and make a PR soon (hopefully also to upload the pre-trained TTS model on the new speaker embedding at the same time)
Describe the bug
PR #5579 broke xvector-conditioned TTS model packaging. In stage 9 of
tts.sh
,spk_xvector.ark
was replaced with{spk_embed_tag}.ark
, which in my recipe resolves toxvector.ark
. That file does not exist whereasspk_xvector.ark
does.Basic environments:
3.9.18 (main, Sep 11 2023, 13:41:44) [GCC 11.2.0]
espnet 202402
pytorch 2.1.0
d0047402e830a3c53e8b590064af4bf70415fb3b
Mon Mar 4 22:19:02 2024 +0000
Task information:
To Reproduce
Steps to reproduce the behavior:
cd egs2/jtubespeech/tts1; ./run.sh --stop-stage 8
./run.sh --stage 9 --stop-stage 9
To Fix
This error originates in the following lines, and can be fixed by modifying lines 1133 and 1134 of tts.sh, changing
{spk_embed_tag}.ark
tospk_{spk_embed_tag}.ark
and{spk_embed_tag}.scp
tospk_{spk_embed_tag}.scp
:espnet/egs2/TEMPLATE/tts1/tts.sh
Lines 1131 to 1135 in ca7716f
I'm not sure whether or how this may affect the new speaker embedding implementation, perhaps the PR author @ftshijt has insight into that?
By the way, thanks for the great work on better integrating speaker embeddings into TTS recipes. I look forward to training an Icelandic speaker embedding model for multi-speaker TTS.
The text was updated successfully, but these errors were encountered: