forked from Blendman974/faceclaw
Bugfixes in iOS Transcribe and Whisper server integration
This commit is contained in:
1 parent
33eef6538c
commit
5bf809d733
12 files changed
+553
-73
No files matched your search
+12
-3
@@ -6,7 +6,11 @@ any OpenAI-compatible Whisper server instead of a cloud service: vLLM, speaches
|
||||
`POST {url}/audio/transcriptions` with a 16 kHz mono WAV. Push-to-talk
|
||||
utterances are one request each; in Transcribe, each span ended by a pause is
|
||||
one request. While a span is open its audio so far is re-sent every 1.5 s, so
|
||||
text appears while you are still talking.
|
||||
text appears while you are still talking. A span that runs 25 s without a pause
|
||||
(nonstop speech, music) is cut at its quietest moment in the last 5 s, so no
|
||||
request outgrows Whisper's 30 s window; the pieces still arrive as one final.
|
||||
On Android the WAV goes out through `FaceclawBinaryPost` (okhttp), since
|
||||
NativeScript's http module copies a binary body into Java a byte at a time.
|
||||
|
||||
## Server
|
||||
|
||||
@@ -39,6 +43,11 @@ before building:
|
||||
## Transcribe on iOS
|
||||
|
||||
Transcribe needs a cloud or Whisper-server provider on iOS (Apple's recognizer
|
||||
only handles short utterances). With "Save Transcribe audio" on (Voice
|
||||
only handles short utterances). Its capture follows the glasses: a disconnect,
|
||||
a glasses lock or backgrounding (for phone-mic capture) transcribes what was
|
||||
already heard, and listening resumes once the glasses reconnect, unlock or the
|
||||
app returns to the foreground. Without a glasses session the phone mic stands in
|
||||
while Faceclaw is in the foreground. With "Save Transcribe audio" on (Voice
|
||||
settings), each session's audio is kept as `transcribe-<time>.wav` in Downloads,
|
||||
next to `transcript-<time>.txt` when the text is saved.
|
||||
next to `transcript-<time>.txt` when the text is saved; a resumed capture keeps
|
||||
appending to the same file.
|
||||
Reference in new issue
Block a user