Open source video conferencing app powered by LiveKit. Built with Django and React.
🔧(summary) add configurable language settings for WhisperX transcription
lebaudantoineaecc48f92822
diff --git a/env.d/development/summary.dist b/env.d/development/summary.distindex e5777226..878fef35 100644--- a/env.d/development/summary.dist+++ b/env.d/development/summary.dist@@ -11,6 +11,7 @@ AWS_S3_SECRET_ACCESS_KEY="password"WHISPERX_BASE_URL="https://configure-your-url.com"WHISPERX_ASR_MODEL="large-v2"WHISPERX_API_KEY="your-secret-key"+WHISPERX_DEFAULT_LANGUAGE="fr"LLM_BASE_URL="https://configure-your-url.com"LLM_API_KEY="dev-apikey"diff --git a/src/helm/env.d/dev-keycloak/values.meet.yaml.gotmpl b/src/helm/env.d/dev-keycloak/values.meet.yaml.gotmplindex 40322953..44f9d245 100644--- a/src/helm/env.d/dev-keycloak/values.meet.yaml.gotmpl+++ b/src/helm/env.d/dev-keycloak/values.meet.yaml.gotmpl@@ -155,6 +155,7 @@ summary:WHISPERX_API_KEY: your-secret-valueWHISPERX_BASE_URL: https://configure-your-url.comWHISPERX_ASR_MODEL: large-v2+ WHISPERX_DEFAULT_LANGUAGE: frLLM_BASE_URL: https://configure-your-url.comLLM_API_KEY: your-secret-valueLLM_MODEL: meta-llama/Llama-3.1-8B-Instruct@@ -191,6 +192,7 @@ celeryTranscribe:WHISPERX_API_KEY: your-secret-valueWHISPERX_BASE_URL: https://configure-your-url.comWHISPERX_ASR_MODEL: large-v2+ WHISPERX_DEFAULT_LANGUAGE: frLLM_BASE_URL: https://configure-your-url.comLLM_API_KEY: your-secret-valueLLM_MODEL: meta-llama/Llama-3.1-8B-Instruct@@ -228,6 +230,7 @@ celerySummarize:WHISPERX_API_KEY: your-secret-valueWHISPERX_BASE_URL: https://configure-your-url.comWHISPERX_ASR_MODEL: large-v2+ WHISPERX_DEFAULT_LANGUAGE: frLLM_BASE_URL: https://configure-your-url.comLLM_API_KEY: your-secret-valueLLM_MODEL: meta-llama/Llama-3.1-8B-Instructdiff --git a/src/summary/summary/core/celery_worker.py b/src/summary/summary/core/celery_worker.pyindex 5a2d5e2f..7e06d2e1 100644--- a/src/summary/summary/core/celery_worker.py+++ b/src/summary/summary/core/celery_worker.py@@ -270,7 +270,9 @@ def process_audio_transcribe_summarize_v2(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+ model=settings.whisperx_asr_model,+ file=audio_file,+ language=settings.whisperx_default_language,)metadata_manager.track(task_id,diff --git a/src/summary/summary/core/config.py b/src/summary/summary/core/config.pyindex 77dc7aa3..b4e39520 100644--- a/src/summary/summary/core/config.py+++ b/src/summary/summary/core/config.py@@ -39,6 +39,8 @@ class Settings(BaseSettings):whisperx_base_url: str = "https://api.openai.com/v1"whisperx_asr_model: str = "whisper-1"whisperx_max_retries: int = 0+ # ISO 639-1 language code (e.g., "en", "fr", "es")+ whisperx_default_language: Optional[str] = Nonellm_base_url: strllm_api_key: strllm_model: str