Record genuine CPU speech and Google lifecycle verification
This commit is contained in:
1 parent
6a3a8bb869
commit
f6b0c8f713
3 files changed
+45
-2
No files matched your search
@@ -46,6 +46,9 @@ Google EmbeddingGemma 2 remains the main text/image/audio/video search model.
|
||||
- [x] Current CPU worker processed real English/German recordings from Unicode
|
||||
paths and reused loaded recognition contexts; this is functional evidence,
|
||||
not independent retrieval or word-timing accuracy.
|
||||
- [x] Genuine shared-service ASR/Google lifecycle passed: verified speech
|
||||
excerpts, zero raw reencodes through policy failure/retry, and retained
|
||||
query reader; [proof](SPEECH-INTEGRATION.md).
|
||||
- [ ] Run genuine shared-service Google lifecycle and frozen independent query
|
||||
controls; stage and deliver the normal hardware-detecting runtime.
|
||||
- [ ] Validate richer no-answer evidence on new independent positive/negative data; do not retune the failed universal cosine cutoff on old held-out results.
|
||||
|
||||
Reference in new issue
Block a user