fishaudio/fish-speech

Issues

• [Feature] Ukrainian language model

  #563 opened 15 days ago by gianpaj
  0

• Help! How can I pull the voice model through the interface and implement TTS in the WeChat TTS plug-in?

  #562 opened 16 days ago by fkucnm
  0

• [BUG] Normal LoRa finetune: Error(s) in loading state_dict for TextToSemantic

  #479 opened 18 days ago by SinanAkkoyun
  2

• Any Possibilities to RUN with Powerful New GEN IGPUs?

  #560 opened 16 days ago by HakaishinShwet
  1

• Generate prompt through Reference Audio "Unsupported backend 'ffmpeg' specified; ", "please select one of ['sox', 'soundfile'] instead."

  #557 opened 17 days ago by Jonathan-Wei
  2

• How to fix the voice across generations ?

  #554 opened 17 days ago by MankaranSingh
  5

• 创建一个微信群供国内用户讨论，并将其放置于显眼位置 (Adding WeChat Group for Chinese users)

  #558 opened 16 days ago by sudo888samewick
  0

• How can i train a new language? [pt-br]

  #549 opened 17 days ago by eletroswing
  1

• [BUG]The results of running the same model on different computers vary greatly.

  #514 opened 25 days ago by tao1261060556
  2

• ModuleNotFoundError: No module named 'ormsgpack'

  #535 opened 18 days ago by one-pip
  5

• Comparison between NaiveTransformer and DualARTransformer

  #546 opened 18 days ago by zsLin177
  1

• [Feature]How can I specify that characters are silent and that pinyin or English words are read automatically?

  #497 opened a month ago by xeoshow
  4

• [BUG]The API call does not seem to support wav and pcm.

  #485 opened a month ago by cqnimin
  2

• Does v1.4 model respect punctuation?

  #542 opened 20 days ago by hoveychen
  3

• ModuleNotFoundError: No module named 'triton.common'

  #541 opened 20 days ago by zn123
  2

• [BUG]The audio generated by the streaming request is noisy. How can I solve this problem?

  #509 opened a month ago by ArvinC
  3

• The expanded size of the tensor (472) must match the existing size (1023) at non-singleton dimension 1.

  #537 opened 20 days ago by lafreak
  6

• Tensor Size Mismatch and `setup_caches` Assertion Error in `generate.py`

  #533 opened 20 days ago by ppmzhang2
  3

• Mac support?

  #532 opened 20 days ago by Pareak
  1

• License terms: what about using this in a commercial product?

  #531 opened 21 days ago by juangea
  3

• Crash when launching new model

  #526 opened 21 days ago by ApatheticWrath
  2

• [BUG] I cannot install fish-speech. Is it related to the pip version?

  #502 opened a month ago by wukongbuku
  6

• ModuleNotFoundError: No module named 'ormsgpack'

  #525 opened 21 days ago by one-pip
  0

• Error occured while finetuning fish-speech-1.4: index 5 is out of bounds for dimension 1 with size 5

  #521 opened 22 days ago by wjddd
  2

• [BUG]ASGI error occurred during WebUI operation

  #511 opened 24 days ago by ievenight
  2

• Why fish-speech implementation of transformer feedforward contains there linears?

  #512 opened a month ago by JohnHerry
  2

• [Feature] Can the online API consider submitting to create the model?

  #494 opened a month ago by 08090813
  4

• [Feature] Improved API interface, no need to provide reference audio and text

  #495 opened a month ago by fastfading
  6

• [BUG] Package name error

  #491 opened a month ago by shinoairisu
  2

• [Bug] toos/api.py reports an error when half inference is enabled

  #496 opened a month ago by litao-zhx
  8

• [BUG] centos, environment installed successfully, various dependency errors

  #503 opened a month ago by wukongbuku
  3

• [BUG] Unable to open WebUI

  #505 opened a month ago by ejiandan
  4

• Which will be better? with indices or with hiddens?

  #492 opened 25 days ago by JohnHerry
  1

• Before you contribute, please read our 'Language Policy'.

  #515 opened 25 days ago by Stardust-minus
  0

• [Feature] How to support new languages

  #489 opened a month ago by ILG2021
  1

• After AutoDL is deployed, the 4090 graphics card uses GPU to infer the length of 1,000 Chinese characters, which takes 37 seconds. Is the audio length of 3 minutes and 10 seconds normal?

  #493 opened 25 days ago by wosuiyu
  2

• [BUG]Unable to continue last training session

  #504 opened 25 days ago by tao1261060556
  6

• [Feature] The current streaming TTS seems to generate speech in the order of requests. Are there any plans to infer multiple requests simultaneously in the future?

  #508 opened 25 days ago by world1tree
  2

• [Feature] Request language support - add dog language clone

  #510 opened a month ago by lujiale621
  1

• [BUG] 按照linux方法安装报错

  #490 opened a month ago by shinoairisu
  10

• llama 训练速度

  #483 opened a month ago by dukGuo
  1

• [BUG]TypeError: cannot unpack non-iterable NoneType object

  #500 opened a month ago by XJF2332
  1

• [BUG] model re-compiled each time, time consuming.

  #501 opened a month ago by didadida-r
  4

• [BUG] API接口调用报错，都是500错误 Internal Server Error

  #488 opened a month ago by zane8521
  1

• [BUG] api推理不支持mp3格式的参考音频

  #475 opened a month ago by Jalen-Zhong
  2

• [BUG] Website reCaptcha error without reCaptcha

  #481 opened a month ago by MInecrafterPictures
  4

• [Feature] Save streaming audio to local path

  #476 opened a month ago by Jalen-Zhong
  1

• 【疑问】语音情感是否支持？

  #480 opened a month ago by l-dawei
  1

• [Feature]Tesla P40这类FP16性能稍差的显卡如何使用FP32精度进行推理？

  #484 opened a month ago by SakuraRK
  0

• [help wanted] faster whisper model的作用

  #474 opened 2 months ago by Jalen-Zhong
  6