mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-29 18:46:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

fix(stt): anchor qwen asr envelope stripping

Browse source
This commit is contained in:
LauraGPT 2026-07-19 05:48:41 +00:00 • committed by Teknium
parent d219392e5b
commit 7d2b8a3cad
2 changed files with 17 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/tools/test_transcription_tools.py
View file

@ -1873,6 +1873,15 @@ class TestExtractTranscriptText:
assert result == "The user literally said <asr_text> while reading markup."
def test_keeps_language_sentence_with_marker_literal(self):
from tools.transcription_tools import _extract_transcript_text
result = _extract_transcript_text(
"Language teachers may say <asr_text> when discussing markup.",
)
assert result == "Language teachers may say <asr_text> when discussing markup."
# Shell safety — shlex.split on auto-detected templates
# ============================================================================

11
tools/transcription_tools.py
View file

@ -30,6 +30,7 @@ Usage::
import logging
import os
import platform
import re
import shlex
import shutil
import subprocess
@ -2094,8 +2095,12 @@ def _extract_transcript_text(transcription: Any) -> str:
if text is None:
text = str(transcription).strip()
marker = "<asr_text>"
if text.lstrip().lower().startswith("language") and marker in text:
text = text.split(marker, 1)[1].strip()
match = re.match(
r"\s*language\s+[\w.-]+(?:\s*<audio_language>[^<]*</audio_language>)?\s*<asr_text>\s*(?P<text>.*)",
text,
flags=re.IGNORECASE | re.DOTALL,
)
if match:
text = match.group("text").strip()
return text