feat(asr): integrate Automatic Speech Recognition (ASR) support

- Added ASR configuration options to the knowledge base and model settings.
- Implemented ASR model selection and transcription capabilities in the knowledge processing pipeline.
- Enhanced file upload support to include audio formats for ASR processing.
- Updated localization files to include ASR-related labels and descriptions.
- Refactored model handling to accommodate ASR as a new model type.
This commit is contained in:
wizardchen
2026-04-02 16:43:37 +08:00
committed by lyingbug
parent d68c94a11a
commit 624e24ba49
30 changed files with 652 additions and 35 deletions
+5
View File
@@ -81,6 +81,11 @@ export interface KBModelConfigRequest {
enabled: boolean
model_id?: string
}
asr_config?: {
enabled: boolean
model_id?: string
language?: string
}
documentSplitting: {
chunkSize: number
chunkOverlap: number