Paul Kompfner
|
913194844e
|
Make the mechanism of adding spaces when concatenating TTS (or speech-to-speech LLM) output text explicit and deterministic, rather than heuristic-based.
This fixes a bug where spaces were sometimes missing from assistant messages in context.
|
2025-11-10 14:22:32 -05:00 |
|
Mark Backman
|
2300941bb8
|
Revert "Merge pull request #3004 from pipecat-ai/mb/improve-concat-aggregated-text"
This reverts commit 5e7f59a0b0, reversing
changes made to 2ad4122b77.
|
2025-11-10 09:58:19 -05:00 |
|
Mark Backman
|
03001f8047
|
Update TranscriptProcessor unit tests
|
2025-11-07 11:44:04 -05:00 |
|
Aleix Conchillo Flaqué
|
9d9f10ae0e
|
frames: StartInterruptionFrame is deprecated, use InterruptionFrame
|
2025-09-11 09:01:54 -07:00 |
|
Aleix Conchillo Flaqué
|
4e3af00b6d
|
tests: try to use default SleepFrame time
|
2025-08-20 10:08:54 -07:00 |
|
Aleix Conchillo Flaqué
|
4015aedb86
|
tests: fix unit tests
|
2025-08-20 10:08:54 -07:00 |
|
Aleix Conchillo Flaqué
|
25dd651757
|
TranscriptionMessage: add user_id field
|
2025-05-19 15:47:54 -07:00 |
|
Aleix Conchillo Flaqué
|
3a37b11e56
|
TranscriptProcessor: send TranscriptionUpdateFrame after interruption
|
2025-04-01 10:21:21 -07:00 |
|
Mark Backman
|
6885d07e88
|
Simplify the TranscriptProcessor _emit_aggregated_text logic
|
2025-03-17 16:36:03 -04:00 |
|
Mark Backman
|
571c10403f
|
tests: Add additional coverage to test_transcript_processor
|
2025-03-17 16:35:35 -04:00 |
|
Mark Backman
|
a49d81e519
|
tests: add tests for TranscriptProcessor
|
2025-02-14 17:10:40 -05:00 |
|