feat/sentence_tokenize_before_TTS #206
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
split large responses into sub-sentences, this improves the TTS synth speed eg, with this PR the sentence below would have been 3 synths instead of 1, and the first one would start playing while it synthed the next 2 > Jan 03 14:55:37 rpi4b hivemind-voice-sat[10648]: 2024-01-03 14:55:37.257 - HiveMind-voice-sat - ovos_audio.service:execute_tts:348 - INFO - Speak: Quantum computing is a field that focuses on developing computer systems that utilize the principles of quantum mechanics. These systems, known as quantum computers, use quantum bits or qubits to process and store information. Unlike classical computers which use bits that can represent either a 0 or a 1, qubits can exist in multiple states simultaneously, thanks to a property called superposition. This allows quantum computers to perform certain calculations much faster than classical computers, potentially enabling breakthroughs in fields like cryptography, optimization, and molecular simulations. However, quantum computing is still a developing field and many practical challenges need to be overcome before fully functional quantum computers become widely available. ChatGPT answered quickly but the TTS server took some time to convert it. It took about 20 seconds with ryan-high on Piper, sure it will be faster with a lower voice but still an issue
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## dev #206 +/- ##
=====================================
Coverage ? 0.00%
=====================================
Files ? 57
Lines ? 4001
Branches ? 0
=====================================
Hits ? 0
Misses ? 4001
Partials ? 0 ☔ View full report in Codecov by Sentry. |
|
confirmed working by @goldyfruit |
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
split large responses into sub-sentences, this improves the TTS synth speed
eg, with this PR the sentence below would have been 3 synths instead of 1, and the first one would start playing while it synthed the next 2
ChatGPT answered quickly but the TTS server took some time to convert it. It took about 20 seconds with ryan-high on Piper, sure it will be faster with a lower voice but still an issue