Use Qwen3-ASR as production speech recognizer

2026-09-25 21:31:33 +02:00
parent 6378b50086
commit 8a323e5b9e
17 changed files with 294 additions and 66 deletions
@@ -158,7 +158,7 @@ function wavFromPcm16(pcm: Buffer, sampleRate = 24000): Buffer {
 }

 // The browser transcription relay sends 8 kHz G.711 mu-law, while Athena's
-// existing Whisper endpoint accepts PCM WAV uploads.
+// transcription endpoint accepts PCM WAV uploads.
 function wavFromMulaw8k(audio: Buffer): Buffer {
  const pcm = Buffer.allocUnsafe(audio.length * 2);
  for (let i = 0; i < audio.length; i += 1) {
@@ -578,7 +578,7 @@ export default definePluginEntry({
  register(api) {
    api.registerRealtimeTranscriptionProvider({
      id: "athena-talk",
-      label: "Athena Whisper (Diktieren)",
+      label: "Athena Qwen3-ASR (Diktieren)",
      defaultModel: "whisper-1",
      models: ["whisper-1"],
      autoSelectOrder: 1,