Thulasiraman/Agentic-AI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

WeLe Agentic AI with Docker deployment

Browse Source
This commit is contained in:
Thulasiraman
2026-08-28 09:19:05 +05:30
parent 6bb0ef25ca
commit 2fb6a0640c
6 changed files with 128 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+7 -4
View File
@@ -58,11 +58,14 @@ ARTIFACT_TTL_HOURS=72
# --- Voice (speech-to-speech, CPU, in-process) ---
# Models are ONNX via Transformers.js — no GPU, no Python, no second service.
# STT onnx-community/whisper-base Tamil + English + language detection
# TTS assets/tts/mms-tts-tam exported locally; no public ONNX exists
# TTS Xenova/mms-tts-eng from the Hub
# STT onnx-community/whisper-tiny.en English only; half the RAM of base
# TTS Xenova/mms-tts-eng from the Hub
# Tamil is built and tested (assets/tts/mms-tts-tam, exported locally — no
# public ONNX exists). Enable it with VOICE_LANGUAGES=en,ta and a multilingual
# STT_MODEL, but budget ~200 MB more resident for the extra voice.
VOICE_LANGUAGES=en
SPEECH_WARMUP=false
STT_MODEL=onnx-community/whisper-base
STT_MODEL=onnx-community/whisper-tiny.en
# Below this confidence, the user's preferred language beats the detector.
DETECT_CONFIDENCE=0.6