huggingface/parler-tts

Issues

• some question to prepare multilinguality training from scratch

  #97 opened 3 months ago by acul3
  3

• Missing argument error

  #151 opened 5 days ago by Goya-ye
  0

• Does not work on macOS with device="mps": "Can't infer missing attention mask on `mps` device"

  #148 opened 15 days ago by ChristianWeyer
  1

• Unknown Error During run_parler_tts_training.py Fine Tuning Process

  #149 opened 13 days ago by lvto2000
  0

• adding a new language

  #128 opened 2 months ago by tculjaga
  11

• Voice Consistency Working Pretty Well -- Plus Zero-Shot Cloning!

  #139 opened a month ago by apresence
  27

• Poor Audio Quality with input_values Input in Parler_TTS

  #81 opened 15 days ago by LiuZH-19
  4

• any list of all 36 voices?

  #95 opened 15 days ago by OpenMachinesAI
  7

• [Documentation Contribution] Voice consistency

  #130 opened 15 days ago by ylacombe
  2

• Voice Cloning through a two step styling process?

  #140 opened a month ago by kaushal-gawri9899
  3

• Is deepspeed simply incompatible with parler?

  #146 opened 23 days ago by left1000
  0

• Training/finetuning dataset for 34 speaker names?

  #145 opened 25 days ago by effusiveperiscope
  0

• Tiny generation slower and yields "IndexError: tuple out of range"

  #144 opened a month ago by ScottMcMac
  0

• Hope to support Chinese.

  #115 opened 2 months ago by mzdk100
  1

• Audio Length Limitation and FlashAttention Warning in Parler TTS

  #126 opened 2 months ago by suman819
  6

• Documentation references to facebook/parler_tts-small

  #117 opened a month ago by rsxdalv
  1

• GREAT MODELS, but a number of issues ...

  #125 opened 2 months ago by apresence
  6

• How big a dataset is needed to train the model?

  #83 opened 4 months ago by zyy-fc
  2

• Profiing problem

  #138 opened a month ago by wxthu
  0

• Numbering pronounce

  #137 opened a month ago by kunci115
  0

• Long audio generation

  #136 opened a month ago by suman819
  0

• Add age too as description.

  #134 opened a month ago by razvanab
  0

• Method depricated problem: torch.nn.utils.weight_norm,SOS

  #133 opened a month ago by ffrgtq
  2

• Why Vocab Size is 1088 ?

  #131 opened 2 months ago by pashanitw
  0

• Questions regarding attention masks in the ParlerTTSDecoder code

  #79 opened 4 months ago by ajd12342
  3

• Error on fine tuning

  #100 opened 2 months ago by xellDart
  10

• Release on pypi?

  #123 opened 2 months ago by haixuanTao
  2

• ValueError: 'dac' is already used by a Transformers config, pick another name.

  #120 opened 2 months ago by tin2tin
  2

• 怎么样支持中文

  #122 opened 2 months ago by anstonjie
  2

• Stream and play

  #114 opened 2 months ago by RobinWitch
  4

• streaming smooth

  #124 opened 2 months ago by cesinsingapore
  3

• Question about the Attention mask for audio tokens (codebooks)

  #121 opened 2 months ago by Jourdelune
  0

• Substitute different Audio codec and Text encoder?

  #119 opened 2 months ago by pracdl314
  0

• How to use italian language?

  #116 opened 2 months ago by piperino11
  0

• Speaker voice is not consistent across different generation

  #112 opened 2 months ago by swapsmagic
  2

• Torch compile problem and some more ideas

  #107 opened 2 months ago by sang-nguyen-ts
  3

• asking for gpu to finetune large model

  #111 opened 2 months ago by kunci115
  1

• Bug in generation code

  #85 opened 4 months ago by Squire-tomsk
  3

• GGML implementation when?

  #99 opened 3 months ago by Kreijstal
  6

• How many epoch of training did you do? What is the accuracy?

  #109 opened 2 months ago by xuezhongfei2008
  0

• [Inference Speed] How we can shorten the inference time per generation?

  #86 opened 4 months ago by rsong0606
  3

• Impact of RoPE and Adding Prompts in Cross Attention on Model Performance

  #106 opened 2 months ago by LiuZH-19
  0

• Request for prompt guide to write description

  #105 opened 2 months ago by gau-nernst
  0

• both small and large checkpoint mispronounces some words

  #104 opened 2 months ago by anurag12-webster
  0

• [Performance] Usage with `optimum-quanto`?

  #92 opened 3 months ago by N3RDIUM
  2

• Alltalk Integration & 1x question re voice consistency

  #96 opened 3 months ago by erew123
  2

• Using static cache and torch.compile, generating more tokens than previously during warmup will trigger graph recapture

  #93 opened 3 months ago by dongngm
  5

• Many Words Cannot be Correctly Read

  #88 opened 3 months ago by bxclib2
  3

• HfHubHTTPError when finetuning

  #90 opened 3 months ago by iakovialexiou
  3

• Special token_ids in tokenizer

  #80 opened 4 months ago by Happenmass
  1