Repository navigation
fix(voz): voz local sem pausas entre os trechos e frase de enviar mais tolerante - #117
Merged
Merged
Conversation
…s tolerante
- Kokoro: um processo por leitura (--serve), o modelo carrega uma vez só.
- Os trechos são gerados sem parar, adiantando enquanto o atual toca; na voz local
crescem 25% por trecho (80 → 600), pra cada um ficar pronto antes do anterior acabar.
- Parar a leitura encerra a voz local na hora.
- "term7 pronto" aceita mais grafias do Whisper ("Tens 7", "Thermo 7", "Ternset",
"Term 7pronto", "pronta"), sempre exigindo o número logo depois.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What / O que muda
--serve(uma linha JSON por trecho): o modelo carrega uma vez por leitura em vez de a cada trecho.mpsc). Na voz local os trechos crescem 25% cada (80 → 600 caracteres), pra cada um ficar pronto antes do anterior acabar de tocar mesmo com 1 núcleo. Pela API continuam 80 + 200, até 600.Medido na máquina de dev (154 caracteres, 9,4 s de fala): 1 núcleo gera em 7,3 s, 3 núcleos em 4,3 s; carregar o modelo ~0,7 s, agora uma vez só.
How to test / Como testar
term7-kokoro --servesome.Checklist
dev, PR todev/ Branch a partir dadev, PR pradevnpm testandnpm run buildpass / passamcargo checkandcargo testpass with no warnings / passam sem warningsscripts/install-local.sh) / Testado no app instalado🤖 Generated with Claude Code