erew123/alltalk_tts

Issues

• RVC model merging and conversion

  #399 opened 21 days ago by bobcate
  0

• Support requests availability & issues

  #377 opened a month ago by erew123
  0

• ROCm MIOpen(HIP) Warning

  #397 opened 22 days ago by NinjaPerson24119
  1

• Version conflict installing requirements_standalone.txt

  #396 opened 22 days ago by SoftologyPro
  4

• Deepspeed

  #394 opened 24 days ago by Gregg245
  2

• bug: alltalk dont start with textgen-web-ui

  #373 opened a month ago by kalle07
  5

• Note - AMD ROCm 6.2 performance issues

  #392 opened a month ago by NinjaPerson24119
  1

• Alltalk TTS beta webui oobabooga on fresh install

  #372 opened a month ago by spike4379
  2

• HELP: is it work now in oobadooga textgenwebui now ?

  #389 opened a month ago by kalle07
  1

• Fine tune, step-1 issue: cudnnCreateTensorDescriptor

  #391 opened a month ago by whynotwork
  2

• Option to Insert Silence between Chunk Outputs in WAV Export

  #390 opened a month ago by GalenMarek14
  0

• Standalone Installation on Windows is not working because FFmpeg installation failed

  #350 opened 2 months ago by Maxwell77HH
  4

• I can't get Deepspeed installed, or cuda being detected....

  #386 opened a month ago by phenix60
  12

• Finetuned Model - Error: Model folder is missing required files or the folder does not exist.

  #387 opened a month ago by theslipperyCarrot
  2

• LibMambaUnsatisfiableError: Encountered problems while solving: - package ffmpeg-7.1.0-lgpl_hdf26e36_401 is excluded by strict repo priority

  #385 opened a month ago by tre4b
  5

• [BUG/Feat]: Voices support mp3's but it only lists wav files

  #380 opened a month ago by phazei
  1

• Request to Continue Updating AllTalk V1

  #384 opened a month ago by StellarBeing25
  3

• Finetuning on GoogleColab fails to launch interface

  #382 opened a month ago by plagasul
  4

• FInetuning with existing transcript in large datasets.

  #363 opened 2 months ago by Dolyfin
  3

• Changed tts engine to parler in script.py webui. No longer launches: ModuleNotFoundError: No module named 'parler_tts'

  #376 opened a month ago by Urammar
  5

• Espeak NG problems and question

  #381 opened a month ago by ShaunCassidyPoster
  4

• xttsv2 (AllTalkV2) Streaming not working on ST (ASGI Exception)

  #379 opened a month ago by PizzaSlice-cmd
  1

• After selecting "Parler" in Gradio, it won't start up: ImportError: cannot import name 'EncoderDecoderCache' from 'transformers.cache_utils'

  #374 opened a month ago by phazei
  4

• Installing Deepseek on Windows

  #375 opened a month ago by maglore9900
  3

• add tortoise TTS?

  #367 opened a month ago by lijackcoder
  2

• Are you adding the New SOTA F5-TTS. This is really impressive

  #371 opened a month ago by maxbizz
  2

• Currently trying to install the extensions for oobabooga/ this applies to standalone as well.

  #370 opened a month ago by spike4379
  0

• Adding the prodigy optimizer in training

  #368 opened a month ago by Mixomo
  0

• Install scripts fails on Linux while attempting to install parler requirements

  #365 opened 2 months ago by Calajese
  2

• How is the BPE tokenizer training supposed to work?

  #362 opened 2 months ago by Mixomo
  2

• I cannot get parler to work on windows10 with alltalk2

  #361 opened 2 months ago by left1000
  8

• I have a bunch of .pth files which are RVC finetunes that I want to use with alltalk

  #360 opened 2 months ago by left1000
  5

• [alltalkbeta] Parler TTS module not found error on fresh install

  #331 opened 3 months ago by teddybear082
  6

• Current Feature Requests List

  #356 opened 2 months ago by erew123
  0

• start_diagnostics.sh fails on Linux due to winreg import

  #358 opened 2 months ago by Paladinium
  2

• finetuning: although EVAL metrics are better, the script does not save the model checkpoint as “best”.

  #359 opened 2 months ago by Mixomo
  2

• Not able to generate Hindi audio using xtts - xttsv2_2.0.3

  #348 opened 2 months ago by nitinmukesh
  7

• DirectML support

  #354 opened 2 months ago by nonetrix
  1

• Missing components after install (ffmpeg.asyncio/sounddevice/Cublas64_11/Visual Studio).

  #353 opened 2 months ago by Jidis83
  4

• TTS Generator leads BSOD and system crashes

  #355 opened 2 months ago by Carlcmd
  3

• alltalk_tts seem to not want to install properly

  #351 opened 2 months ago by phenix60
  1

• Feature Request V2 Beta: Ability to change the configuration file used in script.py

  #349 opened 2 months ago by steampoweredtaco
  8

• ERROR: Exception in ASGI application

  #343 opened 2 months ago by scofano
  7

• Not working on Windows 11 (installing beta version for the first time)

  #347 opened 2 months ago by nitinmukesh
  2

• Mistake with letters

  #337 opened 3 months ago by Mubumbutu
  2

• Error 500 with Silly Tavern

  #338 opened 3 months ago by Webslug
  1

• [alltalkbeta] coqui-tts 0.24.1 requires transformers<4.41.0,>=4.33.0

  #332 opened 3 months ago by xdax1
  3

• [alltalkbeta] Windows standalone installer breaks if conda exists

  #330 opened 3 months ago by DaniDipp
  1

• Bark Integration

  #333 opened 3 months ago by nicoan777
  1

• Multiple voices in generator

  #334 opened 3 months ago by ErnieV
  1