Skip to content

armgit / meet

Public Imported from GitHub
0

Open source video conferencing app powered by LiveKit. Built with Django and React.

✨(summary) add a language parameter for transcription

lebaudantoine4cb6320b832d
diff --git a/src/backend/core/recording/event/notification.py b/src/backend/core/recording/event/notification.py
index 3138b923..89ea5111 100644
--- a/src/backend/core/recording/event/notification.py
+++ b/src/backend/core/recording/event/notification.py
@@ -137,6 +137,7 @@ class NotificationService:
"email": owner_access.user.email,
"sub": owner_access.user.sub,
"room": recording.room.name,
+ "language": recording.options.get("language"),
"recording_date": recording.created_at.astimezone(
owner_access.user.timezone
).strftime("%Y-%m-%d"),
diff --git a/src/summary/summary/api/route/tasks.py b/src/summary/summary/api/route/tasks.py
index 89f20101..02e9f541 100644
--- a/src/summary/summary/api/route/tasks.py
+++ b/src/summary/summary/api/route/tasks.py
@@ -5,7 +5,7 @@ from typing import Optional
from celery.result import AsyncResult
from fastapi import APIRouter
-from pydantic import BaseModel
+from pydantic import BaseModel, field_validator
from summary.core.celery_worker import (
process_audio_transcribe_summarize_v2,
@@ -26,6 +26,18 @@ class TaskCreation(BaseModel):
room: Optional[str]
recording_date: Optional[str]
recording_time: Optional[str]
+ language: Optional[str]
+
+ @field_validator("language")
+ @classmethod
+ def validate_language(cls, v):
+ """Validate 'language' parameter."""
+ if v is not None and v not in settings.whisperx_allowed_languages:
+ raise ValueError(
+ f"Language '{v}' is not allowed. "
+ f"Allowed languages: {', '.join(settings.whisperx_allowed_languages)}"
+ )
+ return v
router = APIRouter(prefix="/tasks")
@@ -44,6 +56,7 @@ async def create_task(request: TaskCreation):
request.room,
request.recording_date,
request.recording_time,
+ request.language,
],
queue=settings.transcribe_queue,
)
diff --git a/src/summary/summary/core/analytics.py b/src/summary/summary/core/analytics.py
index 80be7ad0..e8b8dd55 100644
--- a/src/summary/summary/core/analytics.py
+++ b/src/summary/summary/core/analytics.py
@@ -118,7 +118,7 @@ class MetadataManager:
"retries": 0,
}
- _required_args_count = 8
+ _required_args_count = 9
if len(task_args) != _required_args_count:
logger.error("Invalid number of arguments to enable metadata manager.")
return
diff --git a/src/summary/summary/core/celery_worker.py b/src/summary/summary/core/celery_worker.py
index e12110fa..d99f6a44 100644
--- a/src/summary/summary/core/celery_worker.py
+++ b/src/summary/summary/core/celery_worker.py
@@ -133,6 +133,7 @@ def process_audio_transcribe_summarize_v2(
room: Optional[str],
recording_date: Optional[str],
recording_time: Optional[str],
+ language: Optional[str],
):
"""Process an audio file by transcribing it and generating a summary.
@@ -193,14 +194,16 @@ def process_audio_transcribe_summarize_v2(
try:
logger.info(
- "Querying transcription for %s seconds of audio …", audio_file.info.length
+ "Querying transcription for %s seconds of audio in %s …",
+ audio_file.info.length,
+ language,
)
transcription_start_time = time.time()
with open(temp_file_path, "rb") as audio_file:
transcription = whisperx_client.audio.transcriptions.create(
model=settings.whisperx_asr_model,
file=audio_file,
- language=settings.whisperx_default_language,
+ language=language or settings.whisperx_default_language,
)
transcription_time = round(time.time() - transcription_start_time, 2)
diff --git a/src/summary/summary/core/config.py b/src/summary/summary/core/config.py
index b5b057d6..ee7654a5 100644
--- a/src/summary/summary/core/config.py
+++ b/src/summary/summary/core/config.py
@@ -42,6 +42,7 @@ class Settings(BaseSettings):
whisperx_max_retries: int = 0
# ISO 639-1 language code (e.g., "en", "fr", "es")
whisperx_default_language: Optional[str] = None
+ whisperx_allowed_languages: Set[str] = {"en", "fr"}
llm_base_url: str
llm_api_key: SecretStr
llm_model: str