docs+chore: make streaming claims precise everywhere - #16
Merged
Conversation
The PR #15 README edit collided with the PR #14 wording, duplicating the estimated-boundaries sentence; the engine table still said 'Chunked' uniformly, which is both uninformative and wrong for Google/ElevenLabs-with-timestamps (JSON base64, post-response) and understated Azure/Edge (real-time WS) and sherpa (sentence batches). - README table: Streaming column now distinguishes 'Real-time (WS)', 'Streamed' (as bytes arrive), 'After response (JSON)', and 'Sentence batches' (sherpa) - README streaming bullet: de-duplicated; one accurate paragraph - sherpaonnx_engine: stale 'synthesises the whole clip up-front' doc comments on STREAMING_CHUNK_SIZE/deliver_pcm updated; deliver_pcm removed (dead since the streaming path) and the generate callback now re-chunks batches to the documented 8 KB multi-callback shape instead of emitting one large buffer per sentence
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #14/#15 — the README still didn't tell the whole story:
Real-time (WS)(Azure, Edge),Streamed(bytes-as-they-arrive: all REST MP3/PCM engines),After response (JSON)(Google, ElevenLabswith-timestamps),Sentence batches(Sherpa-ONNX).STREAMING_CHUNK_SIZE's doc still claimed sherpa 'synthesises the whole clip up-front';deliver_pcmwas dead code since feat(sherpaonnx): stream audio per sentence batch via the generate callback #15 — removed, and the generate callback now re-chunks each sentence batch into 8 KB pieces to preserve the documented multi-callback delivery shape (it was emitting one large buffer per sentence).No API or behaviour change beyond chunk sizing. Full lib suite green; live
sherpa_streams_audio_per_sentence_batchre-verified with the real Piper model.