Skip to content

Commit

Permalink
update libraries
Browse files Browse the repository at this point in the history
  • Loading branch information
sachinsshetty committed Dec 4, 2024
1 parent 8a9fa65 commit 0bd3f0d
Show file tree
Hide file tree
Showing 2 changed files with 13 additions and 6 deletions.
15 changes: 11 additions & 4 deletions tutorials/indic/tts/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,15 @@ TTS -
- docker compose -f indic-tts-compose.yml up --detach parler-tts-server

- Test output
- curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?"}' -o audio.mp3
- kannada
- curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "ಉದ್ಯಾನದಲ್ಲಿ ಮಕ್ಕಳ ಆಟವಾಡುತ್ತಿದ್ದಾರೆ ಮತ್ತು ಪಕ್ಷಿಗಳು ಚಿಲಿಪಿಲಿ ಮಾಡುತ್ತಿವೆ."}' -o audio.mp3

- hindi
- curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "अरे, तुम आज कैसे हो?"}' -o audio.mp3

- curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?", "voice": "Feminine, speedy, and cheerfull"}' -o audio_2.mp3

-

---
TODO
Expand All @@ -23,12 +30,12 @@ TODO

- huggingface-cli download parler-tts/parler-tts-mini-expresso

- with fedirz/parler-tts
- with slabstech/parler-tts
- ai4bharat/indic-parler-tts
- huggingface-cli download ai4bharat/indic-parler-tts
- docker run --detach --volume ~/.cache/huggingface:/root/.cache/huggingface --publish 8000:8000 --env MODEL="ai4bharat/indic-parler-tts" fedirz/parler-tts-server
- docker run --detach --volume ~/.cache/huggingface:/root/.cache/huggingface --publish 8000:8000 --env MODEL="ai4bharat/indic-parler-tts" slabstech/parler-tts-server
- parler-tts/parler-tts-mini-expresso
- huggingface-cli download parler-tts/parler-tts-mini-expresso
- docker run --detach --volume ~/.cache/huggingface:/root/.cache/huggingface --publish 8000:8000 --env MODEL="parler-tts/parler-tts-mini-expresso" fedirz/parler-tts-server
- docker run --detach --volume ~/.cache/huggingface:/root/.cache/huggingface --publish 8000:8000 --env MODEL="parler-tts/parler-tts-mini-expresso" slabstech/parler-tts-server

- curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?"}' -o audio.mp3
4 changes: 2 additions & 2 deletions tutorials/indic/tts/indic-tts-compose.yml
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
services:
parler-tts-server:
image: fedirz/parler-tts-server
image: slabstech/parler-tts-server
build:
dockerfile: Dockerfile
context: .
platforms:
- linux/amd64
tags:
- fedirz/parler-tts-server
- slabstech/parler-tts-server
develop:
watch:
- path: ./parler_tts_server
Expand Down

0 comments on commit 0bd3f0d

Please sign in to comment.