root
/
chatterbox
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
33 Commits 3 Branches 1 Tag 14 MiB
Commit Graph

33 Commits

Author SHA1 Message Date
Tedi Papajorgji ed27b95ee4
Fix ReadMe Banner Image (#381) 2025-12-15 11:57:31 -05:00
Ollie McCarthy bc58894bb8
Chatterbox Turbo 350M Model (#380) 
* add gpt2-medium config

* setup turbo-specific hp

* whitespace

* t3 constructor logic

* update gpt2 config values

* fix t3 constructor

* t3 safetensor loading correctly

* everything loading ok

* update from_pretrained method

* inference working

* new inference_turbo method

* avoid tokenizer missing pad error

* connect sampling params to .generate

* add min_p to unused warning

* inference with s3gen distilled

* change to distilled model in from_local

* norm loudness - relax punc norm

* add gradio app

* add silence to end of output wav

* add events to gradio app

* change default text

* new dependencies

* move advanced options to the righthand side of gradio app

* remove russian-text-stresser and bump version

* update readme

* update readme

* resize headings

* links to sections

* typo

* update space link

* chessy emojiis (might remove these later)

* change to single emojii

* remove most emojiis

* Update README.md with new image

* Update README.md remove extra char

* add dedicated turbo example script

---------

Co-authored-by: Zohaib Ahmed <zohaib@resemble.ai>
 2025-12-15 17:01:23 +01:00
manmay nakhashi c375f02ca1
remove russian-stresser from dependency (#377) 2025-12-12 14:00:37 +05:30
Ollie McCarthy c61ec831bd
Make russian-text-stresser optional (#376) 
* Update pyproject.toml

* add automated install check

* udpate to check master - not main
 2025-12-11 16:53:27 +01:00
zihanjin428 bf169fe5f5
Multilingual v2 update (#295) 
* multilingual v2 vocab and russian stresser update

* multilinugal tokenizer fix
 2025-09-25 14:04:48 +09:00
Zohaib Ahmed 1b5ae50585
Update README.md with fixed image link (#236) 2025-09-04 14:53:17 -07:00
zihanjin428 a0434ffb3d
Update README.md (#235) 2025-09-04 23:41:56 +05:30
manmay nakhashi 1798729e3a
remove src (#234) 
* remove src

* bump version 0.1.4

* fix pip
 2025-09-04 23:08:53 +05:30
Tedi Papajorgji a8d8051eb7
Update gradio links (#232) 2025-09-04 09:55:51 -07:00
manmay nakhashi 214fbd197e
bump the version to 0.1.3 (#230) 2025-09-04 20:41:00 +05:30
zihanjin428 a9742ee281
Multilingual implementation (#229) 
* Add multilingual support

* Update model card and README

* Update examples and README

* Remove EOS supression

* Keep EOS supression for longer text

* Update README.md

* Update README.md

* modify tokenizers, set alignment analyzer default to none

* minor fixes, strict forcing EOS

* Update model repo
 2025-09-04 11:04:22 -04:00
Ollie McCarthy 7bfc681408
Update README.md with citation (#213) 2025-08-01 15:52:29 +05:30
askmyteapot eb90621fa7
Enable usage of Min_P Sampler, modify other sampler settings (#155) 
This commit enables the use of min_p sampler, as well as giving the gradio app sliders to configure  top_p, min_p and repetition_penalty

Changed the defaults to min_p=0.05, rep_pen=1.2, top_p=1.0

min_p=0.00 - disables
top_p=1.00 - disables
 2025-06-13 11:26:49 +05:30
Jeremy Hsu a65a3f8374
Clarify OS & Py version; Adjust dependencies (#138) 
* update installation for editable mode

* deps: rm resampy; more flexable numpy

* rm aas from inference

* mv AttrDict our from t3 to models.utils

* replace omegaconfi with AttriDict in S3Gen

* rm omegaconf from deps; re-lint flow.py

* update README

* add OS

* add version
 2025-06-10 09:33:46 +08:00
Tedi Papajorgji b4b55265e9
updated discord join link (#131) 2025-06-07 10:21:47 -07:00
Piotr Kawa aa003f2d66
Feature: Update example scripts, add example wavs, add info on watermarking, safetensor in VC model (#82) 
* update examples, add info on watermarking

* fix: safetensor in VC model

* fix: remove example files
 2025-06-04 21:54:02 +08:00
mrfakename c1af862480
Potentially fix CUDA error (#114) 2025-06-04 12:40:31 +02:00
jin9581 5a1193d603
Merge pull request #80 from resemble-ai/optinal_cfg 
Apply CFG optionally
 2025-05-30 20:25:37 +09:00
manmay-nakhashi 5c4ad7bf54 ability to turn off cfg slider to 0 2025-05-30 11:24:39 +00:00
manmay nakhashi 294890d0e1
Merge pull request #81 from resemble-ai/update_safetensor 
update models from pt to safetensors
 2025-05-30 16:29:54 +05:30
manmay-nakhashi 8a13468805 update librosa to 0.11.0 support for python 3.13 2025-05-30 10:59:13 +00:00
manmay-nakhashi 9cdced61bc bump version 2025-05-30 10:13:59 +00:00
manmay-nakhashi fed5922e98 update models from pt to safetensors 2025-05-30 10:09:08 +00:00
Tedi Papajorgji 5fb5bc87d8
Fix link in readme 2025-05-30 02:25:39 -07:00
jin9581 3a013dc73e Apply CFG optionally based on cfg_weight 2025-05-30 09:03:50 +00:00
Tedi Papajorgji 4f60f98686
Merge pull request #75 from resemble-ai/disc 
Add discord to Readme
 2025-05-29 23:22:09 -07:00
Tedi Papajorgji b74f00680d
add links to discord 2025-05-29 23:19:04 -07:00
Benjamin Bolton df73ac8166
Feature: Add cpu mps support (#35) 
* Ignore generated/local .wav files

* Loosen numpy reqs to installable version

* Attempt to support cpu/mps
 2025-05-29 17:58:13 -04:00
Ollie McCarthy 6742dfee0c
Update README.md (#57) 2025-05-29 14:59:46 +02:00
manmay nakhashi 03c7e3aac0
Merge pull request #40 from serome111/master 
Example for use in mac M*
 2025-05-29 13:39:47 +05:30
Sebastian Roa Meneses 95d235f5ca
Create example_for_mac.py 2025-05-28 19:43:44 -05:00
Sebastian Roa Meneses 230b4a099e
Update README.md 
updated correct info for use
 2025-05-28 19:41:33 -05:00
JeremyCCHsu f42d31ae29 init 
---------

Co-authored-by: fatchord <fatchord@tutanota.com>
Co-authored-by: manmay nakhashi <manmay.nakhashi@gmail.com>
Co-authored-by: John Meade <john.meade@hbar.ca>
Co-authored-by: Zohaib Ahmed<zohaib92@gmail.com>
 2025-05-28 15:57:27 +00:00