idiap/coqui-ai-TTS

Issues

• Remove debug log in inference

  #233 opened 4 days ago by cod3r0k
  1

• Problems using OpenVoice with cuda and >5s source audio

  #234 opened 4 days ago by eginhard
  0

• [Bug] xtts voice generation is better in 0.24.3 than in 0.25 and above

  #228 opened 6 days ago by C00reNUT
  1

• ValueError: The following `model_kwargs` are not used by the model: ['voice_dirs']

  #223 opened 7 days ago by eginhard
  3

• help

  #225 opened 8 days ago by fontnet1
  3

• Add VITS 2 model

  #123 opened 2 months ago by Marioando
  11

• [Bug] Training XTTSv2 leads to weird training lags

  #54 opened 6 months ago by NikitaKononov
  1

• [Feature request] Compatibility with transformers>=4.43.2

  #65 opened 2 months ago by SiriuslySirius
  18

• [Bug] tts-server unable to start with xtts_v2 model

  #99 opened 3 months ago by rohitkrishna094
  1

• Output of --list_speaker_idxs for XTTS should not include latents

  #139 opened 2 months ago by eginhard
  0

• [Feature request] Auralis optimisations of XTTS

  #181 opened a month ago by erew123
  2

• [Bug] Voice cloning issue in coqui-tts 0.25.0

  #198 opened 18 days ago by mirfan899
  2

• [Bug] HIP/AMD not woking >= 0.24.3

  #220 opened 9 days ago by jlucaso1
  1

• [Bug] bokeh 1.4.0 is incompatible with python 3.12

  #218 opened 9 days ago by rhdunn
  1

• [Bug] `tts --list_models` writes to stderr instead of stdout

  #214 opened 10 days ago by AshkanArabim
  2

• 1

  #205 opened 15 days ago by 120805481
  0

• [Bug] Error when building docker image. sudachipy dependency error

  #187 opened 24 days ago by rmajasol
  1

• [feature request]Support Thai

  #177 opened a month ago by K1ndred-zsq
  0

• [Bug] Not getting results

  #164 opened a month ago by Homiee223
  2

• Unclear error message with multi-channel audio

  #153 opened a month ago by madey83
  6

• [Bug] Fix for building docker on arm64 (M1 Mac)

  #160 opened a month ago by hongkongkiwi
  3

• [HELP] Can't get the `tts_models/de/thorsten/tacotron2-DDC` model

  #129 opened a month ago by ZijunSong
  2

• [Bug] 3x RTX 4090 GPUs Insufficient for TTS Model Training?

  #154 opened a month ago by ParadoxTR
  0

• [Bug] Bad results clone voice when loading with model_path and config_path

  #134 opened 2 months ago by OlegRuban-ai
  3

• [Bug] Zoo tests are flaky because of download errors

  #131 opened 2 months ago by eginhard
  2

• [Bug] xttsv2 license acceptance process broken if calling function doesn't provide stdin/stdout access; then coqui fails on next run due to missing files

  #145 opened 2 months ago by ajkessel
  6

• Vits2 / Yourtts2 doesnt work with accelerate

  #148 opened 2 months ago by Marioando
  1

• [Bug] SPEED Missing !!

  #141 opened 2 months ago by sysmaya
  0

• [Feature request] Speakers should be grouped by languages

  #132 opened 2 months ago by FlorianEagox
  1

• torch>=2.4 dependency in dev means no support for Intel Macs

  #112 opened 2 months ago by ajkessel
  2

• [Bug] Voice Conversion to File - Input and parameter tensors are not at the same device, found input tensor at cpu and parameter tensor at cuda:0

  #101 opened 2 months ago by andrea-mucci
  2

• [Bug] Mix language inference text

  #115 opened 2 months ago by cod3r0k
  4

• LiNeS fine-tuning method for XTTS v2 gpt finetuning

  #119 opened 2 months ago by kunibald413
  0

• [Feature request] What is best alternative than eSpeak?

  #116 opened 2 months ago by cod3r0k
  0

• [Bug] Streaming dosn't work | inference_stream is as fast as normal inference

  #97 opened 2 months ago by Fledermaus-20
  4

• [Feature request] Support python 3.13

  #108 opened 2 months ago by jessebot
  2

• [Feature request] FTS (File to speech)

  #89 opened 2 months ago by tigros
  1

• [Feature request] Integrate goruut phonemizer 🚀

  #86 opened 2 months ago by neurlang
  3

• [Bug] Install fails with: No module named 'distutils.msvccompiler'

  #91 opened 3 months ago by KoljaB
  5

• [Feature request] Text for synthesis needs to be normalized for languages with diacritics

  #63 opened 3 months ago by JanX2
  2

• [Feature request] Model quantization

  #82 opened 3 months ago by Dong-mel
  1

• [Bug] Potential vulnerability in TTS model loading due to torch.load default behavior

  #71 opened 3 months ago by ColeDrain
  1

• [Feature request] installation of package without cuda

  #80 opened 3 months ago by skewty
  1

• [Bug] Empty audio is generated and causes ZeroDivisionError

  #69 opened 4 months ago by pablodz
  3

• [Bug] Text duplication while audio generation

  #72 opened 4 months ago by olehsamoilenko
  1

• [Feature request] release gruut dependency constraint

  #68 opened 5 months ago by rsxdalv
  1

• [Feature request] Support latest version of networkx

  #55 opened 5 months ago by ic-mw
  5

• [Bug] Cloning voice add sometimes a noise

  #58 opened 6 months ago by luca2125
  2

• Add access to ModelManager and SpeakerManager

  #42 opened 7 months ago by KoljaB
  3

• Has emotion support only existed for coqui API users?

  #40 opened 7 months ago by matbee-eth
  0