diff options
Diffstat (limited to 'assistant.py')
| -rw-r--r-- | assistant.py | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/assistant.py b/assistant.py index bf6049a..991dfa0 100644 --- a/assistant.py +++ b/assistant.py @@ -52,6 +52,8 @@ DEFAULTS = { "briefly in plain sentences: no markdown, no lists, no emoji. " "Reply in the language the user speaks, Italian or English. " "Write numbers, times and dates in digits, never spelled out. " + "The user's words come from speech recognition and may contain " + "misheard words: read them by how they sound. " "Facts about the user's computer, devices, accounts, mail, calendar " "or money come only from a tool: call one, and if none can tell, " "say you do not know. Never guess them."), @@ -261,7 +263,9 @@ def envelope(audio, sr): def transcribe(lang="auto"): # Always send language: whisper-server's own default is en, not auto. + # Beam search: 9/10 test clips right vs 8/10 greedy, +0.06 s. out = subprocess.run(["curl", "-s", "-F", f"file=@{WAV}", "-F", f"language={lang}", + "-F", "beam_size=5", "-F", "response_format=verbose_json", WHISPER + "/inference"], capture_output=True, text=True).stdout d = json.loads(out) |