fix: use Speechmatics cmn_en bilingual model for Chinese-English mixed speech

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
hailin 2026-03-02 23:57:26 -08:00
parent 1d43943110
commit 17ff9d3ce0
1 changed files with 1 additions and 1 deletions

View File

@ -16,7 +16,7 @@ logger = logging.getLogger(__name__)
# Map Whisper language codes to Speechmatics language codes
_LANG_MAP = {
"zh": "cmn",
"zh": "cmn_en",
"en": "en",
"ja": "ja",
"ko": "ko",