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
Should be resolved as of v0.6.0: word timestamps are now derived for the non-English (espeak-based) voices as well, italian included. Closing, but feel free to reopen if you still get empty captions on a current image.
Activity
lauborges commentedon Apr 9, 2025
Using "language_code": "p" in /dev/captioned_speech parameters with audio in Portuguese, the x-timestamps-path JSON created is an empty JSON array.
xazzazelx commentedon Apr 13, 2025
Same problem, timestamps only works for "a" or "b" :/
remsky commentedon Aug 16, 2026
Should be resolved as of v0.6.0: word timestamps are now derived for the non-English (espeak-based) voices as well, italian included. Closing, but feel free to reopen if you still get empty captions on a current image.