search

leon-ai / leon

🧠 Leon is your open-source personal assistant.
https://getleon.ai
MIT License
15.5k stars 1.28k forks source link

After I turn on STT in .env, the server can not be started up #495

Open xuguoliang1964 opened 1 year ago

xuguoliang1964 commented 1 year ago

Specs

xu@xu-ThinkPad-Edge-E431:/home/leon-ai/leon$ sudo leon check

leon@1.0.0-beta.9+dev check ts-node scripts/check.js

.: CHECKING :. ℹ️ Leon version ✅ 1.0.0-beta.9+dev

ℹ️ Environment ✅ Free RAM: 5.26 | Total RAM: 15.44 GB ✅ {"type":"Linux","platform":"linux","arch":"x64","cpus":8,"release":"5.19.0-41-generic","osName":"Linux 5.19","distro":{"os":"linux","dist":"Ubuntu","codename":"jammy","release":"22.04"}}

ℹ️ node --version ✅ v18.16.0

ℹ️ npm --version ✅ 9.5.1

✅ Node.js bridge version: 0.0.1-alpha.0 ℹ️ Executing a skill... ℹ️ /home/leon-ai/leon/node_modules/ts-node/dist/bin.js --swc /home/leon-ai/leon/bridges/nodejs/dist/bin/leon-nodejs-bridge.js "/home/leon-ai/leon/scripts/assets/nodejs-bridge-intent-object.json" ✅ [WIP] Node.js bridge 0.0.1-alpha.0 ℹ️ Skill execution time: 407ms

✅ Python bridge version: 1.0.1 ℹ️ Executing a skill... ℹ️ /home/leon-ai/leon/bridges/python/dist/linux-x86_64/leon-python-bridge "/home/leon-ai/leon/scripts/assets/python-bridge-intent-object.json" ✅ {"domain": "leon", "skill": "random_number", "action": "run", "lang": "en", "utterance": "Give me a random number", "entities": [], "slots": {}, "output": {"type": "end", "codes": ["33"], "speech": "33", "core": {}, "options": {}}} ℹ️ Skill execution time: 321ms

✅ TCP server version: 1.0.0 ℹ️ Starting the TCP server... ℹ️ /home/leon-ai/leon/tcp_server/dist/linux-x86_64/leon-tcp-server en ✅ The TCP server can successfully start ℹ️ TCP server startup time: 11372ms

ℹ️ Global resolvers NLP model state ✅ Found and valid

ℹ️ Skills resolvers NLP model state ✅ Found and valid

ℹ️ Main NLP model state ✅ Found and valid

ℹ️ Amazon Polly TTS ⚠️ Amazon Polly TTS is not yet configured

ℹ️ Google Cloud TTS/STT ⚠️ Google Cloud TTS/STT is not yet configured

ℹ️ Watson TTS ⚠️ Watson TTS is not yet configured

ℹ️ Offline TTS ✅ Found Flite at bin/flite/flite

ℹ️ Watson STT ⚠️ Watson STT is not yet configured

ℹ️ Offline STT ✅ Found Coqui language model at bin/coqui/huge-vocabulary.scorer

.: REPORT :. ℹ️ Here is the diagnosis about your current setup ✅ Run ✅ Run skills ✅ Reply you by texting ✅ Start the TCP server ⚠️ Amazon Polly text-to-speech ⚠️ Google Cloud text-to-speech ⚠️ Watson text-to-speech ✅ Offline text-to-speech ⚠️ Google Cloud speech-to-text ⚠️ Watson speech-to-text ✅ Offline speech-to-text

✅ Hooray! Leon can run correctly ℹ️ If you have some yellow warnings, it is all good. It means some entities are not yet configured

.: REPORT URL :. ℹ️ Sending report... ✅ Report URL: https://report.getleon.ai/raw/exarezeyup

Expected Behavior

"leon start" brings server up.

Actual Behavior

"leon start" exit without server in running status

How Do We Reproduce?

Turn on STT in .env like this:

Enable/disable Leon's speech-to-text

LEON_STT=true

Speech-to-text provider

LEON_STT_PROVIDER=coqui-stt

run "leon start"

Extra (like a sample repo to reproduce the issue, etc.)

Teminal message after running "leon start" xu@xu-ThinkPad-Edge-E431:/home/leon-ai/leon$ sudo leon start

leon@1.0.0-beta.9+dev start cross-env LEON_NODE_ENV=production node server/dist/pre-check.js && node server/dist/index.js

.: PRE-CHECKING :. ℹ️ Checking system requirements... ✅ Minimum required RAM: 4 GB | Free RAM: 5 | Total RAM: 15 GB ℹ️ Checking voice configuration schemas... ✅ Voice configuration schemas checked ℹ️ Checking global data schemas... ✅ Global data schemas checked ℹ️ Checking skills data schemas... ✅ Skills data schemas checked

.: TCP CLIENT :. ✅ New instance

.: HTTP SERVER :. ✅ New instance

.: SOCKET SERVER :. ✅ New instance

.: STT :. ✅ New instance

.: TTS :. ✅ New instance

.: ASR :. ✅ New instance

.: NER :. ✅ New instance

.: MODEL LOADER :. ✅ New instance

.: CONVERSATION :. ✅ New instance

.: NLU :. ✅ New instance

.: BRAIN :. ✅ New instance

.: INITIALIZATION :. ℹ️ The current env is production ℹ️ The current version is 1.0.0-beta.9+dev ℹ️ The current time zone is America/New_York ℹ️ Telemetry enabled

.: STT :. ℹ️ Initializing STT...

.: INITIALIZATION :. ✅ Server is available at http://localhost:1337 xu@xu-ThinkPad-Edge-E431:/home/leon-ai/leon$ xu@xu-ThinkPad-Edge-E431:/home/leon-ai/leon$ sudo leon start

leon@1.0.0-beta.9+dev start cross-env LEON_NODE_ENV=production node server/dist/pre-check.js && node server/dist/index.js

.: PRE-CHECKING :. ℹ️ Checking system requirements... ✅ Minimum required RAM: 4 GB | Free RAM: 5 | Total RAM: 15 GB ℹ️ Checking voice configuration schemas... ✅ Voice configuration schemas checked ℹ️ Checking global data schemas... ✅ Global data schemas checked ℹ️ Checking skills data schemas... ✅ Skills data schemas checked

.: TCP CLIENT :. ✅ New instance

.: HTTP SERVER :. ✅ New instance

.: SOCKET SERVER :. ✅ New instance

.: STT :. ✅ New instance

.: TTS :. ✅ New instance

xu@xu-ThinkPad-Edge-E431:/home/leon-ai/leon$

screen shot after running "leon start" image

xuguoliang1964 commented 1 year ago

TTS works with current version well. After I turn STT on, leon failed to bring the server up.

amoussa646 commented 1 year ago

any updates on this? im facing the same issue

abasllari commented 7 months ago

same issue , any update please ?

rstuhlmuller commented 5 months ago

Same issue here, seems to work when using AWS polly, but fails when running the "offline" setup (coqui-stt)

gagipro commented 2 weeks ago

Same here