ben.carrasco/jambonz-feature-server
1
0
Fork 0
mirror of https://github.com/jambonz/jambonz-feature-server.git synced 2025-12-18 20:07:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix/flux cleanup (#1379)

Browse Source 
* for deepgram flux include the turn taking events in the transcription payload

* for deepgram flux, including turn_taking_event in the speech payload

* fix prev commit which used wrong field
This commit is contained in:
Dave Horton
2025-10-04 20:06:38 -04:00
committed by GitHub
parent 854c26db11
commit d2d3b4583e
3 changed files with 19 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
lib/utils/transcription-utils.js
View File

@@ -339,16 +339,28 @@ const normalizeDeepgram = (evt, channel, language, shortUtterance) => {
};
};
const normalizeDeepgramFlux = (evt, channel, language, shortUtterance) => {
const normalizeDeepgramFlux = (evt, channel, language) => {
const copy = JSON.parse(JSON.stringify(evt));
let turnTakingEvent;
if (['StartOfTurn', 'EagerEndOfTurn', 'TurnResumed', 'EndOfTurn'].includes(evt.event)) {
turnTakingEvent = evt.event;
}
/* calculate total confidence based on word-level confidence */
const realWords = (evt.words || [])
.filter((w) => ![',.!?;'].includes(w.word));
const confidence = realWords.length > 0 ? realWords.reduce((acc, w) => acc + w.confidence, 0) / realWords.length : 0;
return {
language_code: language,
channel_tag: channel,
is_final: evt.event === 'EndOfTurn',
alternatives: [
{
confidence: evt.end_of_turn_confidence,
confidence,
end_of_turn_confidence: evt.end_of_turn_confidence,
transcript: evt.transcript,
...(turnTakingEvent && {turn_taking_event: turnTakingEvent})
}
],
vendor: {
@@ -967,7 +979,6 @@ module.exports = (logger) => {
}
else if ('deepgramflux' === vendor) {
const {
preflightThreshold,
eotThreshold,
eotTimeoutMs,
mipOptOut,
@@ -978,7 +989,6 @@ module.exports = (logger) => {
opts = {
DEEPGRAMFLUX_API_KEY: sttCredentials.api_key,
DEEPGRAMFLUX_SPEECH_MODEL: model || 'flux-general-en',
...(preflightThreshold && {DEEPGRAMFLUX_SPEECH_PRELIGHT_THRESHOLD: preflightThreshold}),
...(eotThreshold && {DEEPGRAMFLUX_SPEECH_EOT_THRESHOLD: eotThreshold}),
...(eotTimeoutMs && {DEEPGRAMFLUX_SPEECH_EOT_TIMEOUT_MS: eotTimeoutMs}),
...(mipOptOut && {DEEPGRAMFLUX_SPEECH_MIP_OPT_OUT: mipOptOut}),

9
package-lock.json generated
View File

@@ -18,7 +18,7 @@
"@jambonz/speech-utils": "^0.2.24",
"@jambonz/stats-collector": "^0.1.10",
"@jambonz/time-series": "^0.2.14",
"@jambonz/verb-specifications": "^0.0.115",
"@jambonz/verb-specifications": "^0.0.116",
"@modelcontextprotocol/sdk": "^1.9.0",
"@opentelemetry/api": "^1.8.0",
"@opentelemetry/exporter-jaeger": "^1.23.0",
@@ -1520,10 +1520,9 @@
}
},
"node_modules/@jambonz/verb-specifications": {
"version": "0.0.115",
"resolved": "https://registry.npmjs.org/@jambonz/verb-specifications/-/verb-specifications-0.0.115.tgz",
"integrity": "sha512-T2J5skCZBADaxePkFqpm0JYwr5Iu6e9zgvk6j0/4vD6lwK29GSoSdk2LCKUY6VH2GYdaN6r3dyIw4xpFVXuMfQ==",
"license": "MIT",
"version": "0.0.116",
"resolved": "https://registry.npmjs.org/@jambonz/verb-specifications/-/verb-specifications-0.0.116.tgz",
"integrity": "sha512-EFAtwSpSWA12nk7eQfAiWS0bGkCA5+NqKsylnVIXNWuSjRZ5wTS0dAZZZxqtZxPZ1DxdBLCafbLsKZJ4fkC+tQ==",
"dependencies": {
"debug": "^4.3.4",
"pino": "^8.8.0"

2
package.json
View File

@@ -34,7 +34,7 @@
"@jambonz/speech-utils": "^0.2.24",
"@jambonz/stats-collector": "^0.1.10",
"@jambonz/time-series": "^0.2.14",
"@jambonz/verb-specifications": "^0.0.115",
"@jambonz/verb-specifications": "^0.0.116",
"@modelcontextprotocol/sdk": "^1.9.0",
"@opentelemetry/api": "^1.8.0",
"@opentelemetry/exporter-jaeger": "^1.23.0",