valenti/vocero-client
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: standardize developer text and identifiers in English

Browse Source
This commit is contained in:
alvaro
2026-10-05 10:13:25 -03:00
parent 6b8c27fd76
commit dfc1f663c7
20 changed files with 933 additions and 1142 deletions
Download Patch File Download Diff File Expand all files Collapse all files
speech_to_speech/TTS/qwen3_tts_handler.py
+16 -19
View File
@@ -13,16 +13,15 @@ import re
import tempfile
import unicodedata
# 2026-09-25 SANITIZE APIPILOT MARKERS PRIMA DI TTS (anti-leak pronunciato da Qwen3).
# Lato server S2S Python abbiamo gia' gate + sanitize ma come DOPPIA RETE
# di sicurezza sanitizziamo DIRETTAMENTE il testo che entra in Qwen3-TTS.
# Formati osservati reali oggi:
# (a) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>> standard 3 parentesi
# Sanitize ApiPilot markers directly before TTS as an additional safeguard
# alongside the S2S relay's audio gating and sanitization.
# Observed formats:
# (a) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>> standard triple brackets
# (b) <APIPILOT_CALL:NAME=tool,ARGUMENTS={"format":"voice"}
# singolo < > (caso user oggi)
# (c) <<<APIPILOT_CALL:...}> \n>> spezzato piu' righe
# (d) >>>APIPILOT_CALL:...<<< invertito
# Regola: CALL -> placeholder spagnolo (frase naturale utente), RESULT -> strip.
# single brackets
# (c) <<<APIPILOT_CALL:...}> \n>> split across lines
# (d) >>>APIPILOT_CALL:...<<< inverted brackets
# Replace CALL with a natural Spanish utterance; strip RESULT markers.
_APIPILOT_CALL_NORMAL_RE = re.compile(
r"[<]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[>]{1,3}",
re.IGNORECASE | re.DOTALL,
@@ -39,7 +38,7 @@ _APIPILOT_SPANISH_PLACEHOLDER = "Voy a consultar tus datos, un momento por favor
def _tts_sanitize_apipilot_markers(text: str) -> tuple[str, bool, str]:
"""Rimuove marker APIPILOT dal testo TTS.
"""Remove ApiPilot markers from TTS text.
Returns (sanitized_text, found_any, log_tag).
"""
@@ -48,7 +47,7 @@ def _tts_sanitize_apipilot_markers(text: str) -> tuple[str, bool, str]:
found_call = False
found_result = False
tool_name = ""
# 1) marker CALL standard + invertito -> placeholder spagnolo
# 1) Replace standard/inverted CALL markers with the Spanish placeholder.
def _repl_call(m: re.Match) -> str:
nonlocal found_call, tool_name
found_call = True
@@ -62,11 +61,11 @@ def _tts_sanitize_apipilot_markers(text: str) -> tuple[str, bool, str]:
text2 = _APIPILOT_CALL_NORMAL_RE.sub(_repl_call, text)
if not found_call:
text2 = _APIPILOT_CALL_INVERTED_RE.sub(_repl_call, text2)
# 2) marker RESULT -> strip silenzioso (non sono pronunciabili)
# 2) Strip RESULT markers silently; they must not be spoken.
if _APIPILOT_RESULT_RE.search(text2):
found_result = True
text2 = _APIPILOT_RESULT_RE.sub(" ", text2)
# 3) safety: FRAMMENTI marker singoli che non hanno wrapper completo
# 3) Catch marker fragments without a complete wrapper.
low = text2.lower()
if "apipilot" in low and ("call" in low or "result" in low):
import re as _re_sf
@@ -782,18 +781,16 @@ class Qwen3TTSHandler(BaseHandler[TTSIn, TTSOut]):
coalesced_text, _language_code, _saw_end_of_response = self._coalesce_pending_tts_input(tts_input)
raw_text = coalesced_text or "Hello."
# 2026-09-25 SANITIZE APIPILOT PRIMA DI TTS (doppia rete sicurezza):
# Anche se lato server S2s Python abbiamo gia' gate audio drop + sanitize,
# Qwen3-TTS puo' ricevere marker per race / nuovi formati. Quindi QUI
# eliminiamo / sostituiamo con placeholder PRIMA di chiamare generate().
# A race or a new marker format can bypass relay sanitization. Strip or
# replace markers again before passing text to the TTS model.
text, found_marker, sanitize_tag = _tts_sanitize_apipilot_markers(raw_text)
if found_marker:
logger.warning(
"[TTS-APIPILOT-SANITIZE] marker=%s rawLen=%d sanitizedLen=%d → sostituito con placeholder spagnolo / strip.",
"[TTS-APIPILOT-SANITIZE] marker=%s rawLen=%d sanitizedLen=%d → replaced with the Spanish placeholder or stripped.",
sanitize_tag, len(raw_text or ""), len(text or ""),
)
if not text.strip():
# Safety se il marker era l'unica cosa: ripetiamo placeholder invece di Hello.
# Use the Spanish placeholder when the marker was the entire utterance.
text = _APIPILOT_SPANISH_PLACEHOLDER
model_type = self._model_type()