engineering/www.unturf.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

zebra-spaces: deploy whisper hallucination filter

Browse source
This commit is contained in:
russell@unturf.com 2026-06-05 13:06:55 -04:00
parent b7b910e4c4
commit 224f2e9f31
No known key found for this signature in database
1 changed files with 49 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

55
zebra-report/zebra-spaces.html
View file

@ -2048,8 +2048,23 @@ class WhisperCaptureProcessor extends AudioWorkletProcessor {
}
this.decimateCounter = (this.decimateCounter + ch.length) % this.decimationFactor;
if (this.bufPos >= this.chunkTargetSamples){
const chunk = this.buf.slice(0, this.bufPos);
this.port.postMessage({ chunk }, [chunk.buffer]);
/* RMS-based silence gate. whisper-tiny.en hallucinates common
* stop-words ("you", "thank you", "thanks for watching", ".")
* when fed silence — even with the mic closed. Skip chunks
* whose energy is below the speech threshold entirely. Saves
* CPU AND suppresses the hallucinated lines.
* Fox 2026-06-05: "this happens even when mic is closed." */
let sumSq = 0;
for (let i = 0; i < this.bufPos; i++){
const s = this.buf[i];
sumSq += s * s;
}
const rms = Math.sqrt(sumSq / this.bufPos);
const SILENCE_THRESHOLD = 0.005; /* ~ -46 dBFS, well below speech */
if (rms >= SILENCE_THRESHOLD){
const chunk = this.buf.slice(0, this.bufPos);
this.port.postMessage({ chunk }, [chunk.buffer]);
}
this.bufPos = 0;
}
return true;
@ -2104,6 +2119,26 @@ async function ensureWhisperPipeline(){
}
let transcribeEnabled = false;
/* whisper-tiny.en hallucinations on silence / low-energy chunks. The
* RMS gate in the capture worklet catches dead silence; this set
* catches what gets past it — quiet-room ambient with the same
* spurious outputs ("you", "thanks for watching", "thank you.", a
* lone period). Lowercased + trimmed of trailing punctuation for
* matching. List grows as new hallucinations are observed. */
const WHISPER_HALLUCINATIONS = new Set([
'you', 'thank you', 'thanks', 'thanks for watching',
'thanks for watching!', 'thank you for watching',
'thank you for watching.', 'thanks for watching.',
'bye', 'okay', 'mm', 'mhm', 'uh huh', 'ah', 'oh',
'um', 'uh', 'hmm', 'yeah', 'yes', 'no', 'ok', 'so',
'and', 'the', 'a', 'i', 'it', 'we',
'.', '..', '...', '!', '?'
]);
/* per-uuid dedupe of the most recent emitted line. whisper sometimes
* re-emits the same short phrase across consecutive chunks even when
* the speaker has paused — looks like spam in the log. */
const _lastTranscriptByUuid = new Map();
function appendTranscriptLine(uuid, text){
const log = document.getElementById('transcript-log');
if (!log) return;
@ -2142,8 +2177,16 @@ async function startCaptureForUuid(uuid){
try {
const result = await pipeline(e.data.chunk, { sampling_rate: 16000 });
const txt = (result && result.text ? result.text : '').trim();
/* skip empty / placeholder transcriptions ("." " " "[BLANK_AUDIO]" etc.) */
if (txt.length >= 2 && !/^\[/.test(txt)) appendTranscriptLine(uuid, txt);
if (txt.length < 2) return;
if (/^\[/.test(txt)) return; /* "[BLANK_AUDIO]" etc. */
/* normalize for hallucination match: lowercase, strip trailing
* punctuation. "You." / "you" / " YOU!" all collapse to "you". */
const norm = txt.toLowerCase().replace(/[.!?,;:\s]+$/,'').trim();
if (WHISPER_HALLUCINATIONS.has(norm)) return;
/* consecutive-duplicate suppression per speaker */
if (_lastTranscriptByUuid.get(uuid) === txt) return;
_lastTranscriptByUuid.set(uuid, txt);
appendTranscriptLine(uuid, txt);
} catch (err){
logLine('err', 'whisper transcribe '+uuid.slice(0,4)+': '+err.message);
}
@ -7117,8 +7160,8 @@ logLine('', 'ready — pick a handle, type a rendezvous code, enter the space');
<footer style="margin:2.2rem auto 0;font-size:0.65rem;color:#999;line-height:1.7;word-break:break-all;font-family:monospace">
<span id="pi-seal" style="color:#777;cursor:default;user-select:none" title="">page integrity</span> &nbsp;·&nbsp; built <span class="stamp-date">2026-06-05</span><br>
md5 <span class="stamp-md5">66fd5efdb6e64d748dbca14181864f64</span><br>
sha256 <span class="stamp-sha">2216311e5dacc548b5c5364b10acce241b5baaa7c2068ca169e749478d5e5fe6</span><br>
md5 <span class="stamp-md5">2773c799f927f392736fa437c9af62e2</span><br>
sha256 <span class="stamp-sha">c4fae24ca1a2a75c5893c4b4498cac724bdaddeb9ba351f758f8aafe3c96df77</span><br>
<span style="color:#bbb">hashes are of this page with these two fields zeroed — to verify, blank them and re-hash</span><br>
<span style="color:#bbb">one self-contained file — <strong>save a copy</strong> and verify against these hashes; point at your own servers with ?signal= and ?turncred=, or <a href="host-your-own.html" style="color:#999">host your own community</a></span>
</footer>