Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / fishaudio/fish-speech issues and pull requests

#431 - Fix the lisense in docs

Pull Request - State: closed - Opened by PoTaTo-Mika 3 months ago

#430 - Clarification on License Terms

Issue - State: closed - Opened by ryan-minato 3 months ago - 1 comment
Labels: bug

#429 - [Feature] hello,could it generate the audio phoneme delayedtime sequence such azure?

Issue - State: open - Opened by CasonTsai 3 months ago - 1 comment
Labels: enhancement

#428 - 使用LORA

Issue - State: closed - Opened by one-pip 4 months ago - 16 comments
Labels: bug

#427 - Load faster whisper model

Issue - State: closed - Opened by one-pip 4 months ago - 1 comment
Labels: bug

#426 - [BUG]推理阶段，超过4096报错

Issue - State: closed - Opened by pengyuange 4 months ago - 1 comment
Labels: bug

#424 - 大家也有丢字的情况嘛？请问有什么好的方式优化嘛？[BUG]

Issue - State: closed - Opened by gllhjy 4 months ago - 1 comment
Labels: bug

#423 - [Feature] v1.2如何训练firefly_gan_vq

Issue - State: closed - Opened by jwang1993 4 months ago - 1 comment
Labels: enhancement

#422 - [Feature] About compill the model first

Issue - State: closed - Opened by PyQiMing 4 months ago
Labels: enhancement

#421 - [BUG] Segmentation fault in inference

Issue - State: open - Opened by MengWenkui 4 months ago - 4 comments
Labels: bug

#418 - [BUG] 运行窗口出现如下代码，单击后程序自动退出。

Issue - State: closed - Opened by geforce213 4 months ago - 2 comments
Labels: bug

#417 - [Feature] existing streaming latency is still takes time,

Issue - State: closed - Opened by kunci115 4 months ago - 6 comments
Labels: enhancement, stale

#416 - [BUG] 推理的时候，使用codes_0.npy 和 codes_1.npy 有什么区别

Issue - State: closed - Opened by pengyuange 4 months ago - 1 comment
Labels: bug

#413 - [BUG]OSError: [Errno -9996] Invalid output device (no default output device)

Issue - State: closed - Opened by pengyuange 4 months ago - 2 comments
Labels: bug

#409 - [Feature] Are there any pause tags?

Issue - State: closed - Opened by myrisc 4 months ago - 3 comments
Labels: enhancement

#408 - [Bug] After fine-tuning the llama model, no fine-tuned checkpoints folder is generated

Issue - State: closed - Opened by lbl1120 4 months ago - 2 comments
Labels: bug

#406 - Ask some experience in fine-tuning the dataset construction.

Issue - State: closed - Opened by jizh18 4 months ago - 1 comment
Labels: enhancement

#403 - [BUG] Audio streaming only available if source is 'microphone' on Ubuntu 22.04

Issue - State: closed - Opened by j2l 4 months ago - 4 comments
Labels: bug, stale

#398 - [Bug] Unlimited processing during inference

Issue - State: closed - Opened by gaoxuxu110 4 months ago - 6 comments
Labels: bug

#388 - [Feature] Is it possible to continue training from the last finetuned checkpoint?

Issue - State: closed - Opened by chunping-xt 4 months ago - 2 comments
Labels: enhancement, stale

#387 - [BUG]在使用官方提供的在线服务时出现大段的静音

Issue - State: closed - Opened by TheHonestBob 4 months ago
Labels: bug

#383 - [Feature] Add other languages

Issue - State: open - Opened by mustapa0 4 months ago - 7 comments
Labels: enhancement

#380 - [Frature] Does it support Cantonese/Cantonese?

Issue - State: open - Opened by macauhome 4 months ago - 2 comments
Labels: enhancement

#377 - [Feature] use text to describe and control the sound style

Issue - State: closed - Opened by chunping-xt 4 months ago - 3 comments
Labels: enhancement

#370 - [BUG] finetune w/o lora, inference get error: Negative code found: {codes}

Issue - State: closed - Opened by sairin1202 4 months ago - 5 comments
Labels: bug, stale

#364 - [BUG]在checkpoint上继续训练会报错

Issue - State: closed - Opened by a-3pig 4 months ago - 4 comments
Labels: bug

#362 - [Feature] some idea for support chinese dialect

Issue - State: open - Opened by shuxiang 4 months ago - 14 comments
Labels: enhancement

#357 - [BUG]克隆声音效果很不好

Issue - State: closed - Opened by lonngxiang 4 months ago - 4 comments
Labels: bug

#356 - [QUESTION] Support on MacOS apple silicon

Issue - State: closed - Opened by limingchina 4 months ago - 8 comments

#346 - [Bug] Docker container cannot be accessed after starting the program

Issue - State: open - Opened by monkeyGeek369 4 months ago - 15 comments
Labels: bug

#338 - [Feature] Is there a tone mark?

Issue - State: open - Opened by yuanjie-ai 4 months ago - 1 comment
Labels: enhancement

#337 - 数据集格式

Issue - State: closed - Opened by decajcd 4 months ago - 1 comment
Labels: enhancement

#336 - [Feature]可以支持法语吗？

Issue - State: closed - Opened by xeoshow 4 months ago - 6 comments
Labels: enhancement

#331 - Support for More Languages

Issue - State: closed - Opened by AnitaLiu98 4 months ago - 2 comments
Labels: enhancement, stale

#329 - 现在最多支持多少个字符输入呢。稍微长一点就提示超过Text too long

Issue - State: closed - Opened by zhouhounan 4 months ago - 1 comment
Labels: enhancement

#328 - [BUG] 语音合成无法识别“啊”这个字，显示fail to fetch

Issue - State: closed - Opened by Scott-Einstein 4 months ago - 1 comment
Labels: bug

#323 - [docx]:delete speaker param in docs

Pull Request - State: closed - Opened by Whale-Dolphin 4 months ago - 1 comment

#322 - [BUG] 使用docker安装，使用webui测试发现的问题

Issue - State: closed - Opened by fallbernana123456 4 months ago - 7 comments
Labels: bug, stale

#320 - [Feature]可以直接把输入音频转化成新的音色的音频，而不使用TTS吗(直接VC)

Issue - State: closed - Opened by sekkit 4 months ago - 3 comments
Labels: enhancement, stale

#319 - [Feature] German Language Model?

Issue - State: closed - Opened by Padi2312 4 months ago - 2 comments
Labels: enhancement, stale

#299 - [BUG] VITS微调时报错

Issue - State: closed - Opened by SnowFox4004 4 months ago - 1 comment
Labels: bug

#291 - [BUG] 安装环境时pytorch下载速度慢

Issue - State: closed - Opened by Touch-Night 5 months ago - 5 comments
Labels: bug

#286 - 关于调用API 生成流式音频的BUG反馈

Issue - State: closed - Opened by hotdogarea 5 months ago - 12 comments
Labels: bug, stale

#243 - 每次推理效果不一样[Feature]

Issue - State: closed - Opened by Ranzige 6 months ago - 4 comments
Labels: enhancement

#233 - 说话人会有概率加入到语音生成出来[BUG]

Issue - State: closed - Opened by only-ns 6 months ago - 4 comments
Labels: bug, stale

#224 - [BUG]使用API接口进行推理，参考音频是女生，生成的是男生

Issue - State: closed - Opened by wuye901126 6 months ago - 9 comments
Labels: bug

#211 - [BUG] dependencies samplerate could not install on centos9

Issue - State: closed - Opened by zergtant 6 months ago - 14 comments
Labels: bug

#207 - New language training - Thai [Feature]

Issue - State: closed - Opened by TanZhili 6 months ago - 7 comments
Labels: enhancement, stale

#203 - please add support for hindi language or documents

Issue - State: closed - Opened by iamjamilkhan 6 months ago - 6 comments
Labels: enhancement

#189 - [BUG] create_train_split.py create wrong path when FT VITS

Issue - State: closed - Opened by AliceNavigator 6 months ago - 2 comments
Labels: bug

#187 - Has anyone successfully run on macos?

Issue - State: closed - Opened by Lynds-007 6 months ago - 4 comments
Labels: enhancement

#148 - 只传入text时，如何固定说话人？

Issue - State: closed - Opened by wac81 6 months ago - 5 comments
Labels: bug

#104 - [Feature] Discussions about the choice of VQ

Issue - State: closed - Opened by wehos 8 months ago - 7 comments
Labels: enhancement

#102 - performance optimize

Pull Request - State: closed - Opened by Stardust-minus 8 months ago - 4 comments

#101 - inference推理效果还行，generate后再用inference生成的人声效果就较差

Issue - State: closed - Opened by FrozenZero 9 months ago - 3 comments
Labels: bug

#100 - 从头训练llama

Issue - State: closed - Opened by WangGewu 9 months ago - 6 comments

#99 - 合成音频内容与text不同，且内容无意义

Issue - State: closed - Opened by WangGewu 9 months ago - 3 comments

#98 - 怎么能保持多句合成之间语气稳定

Issue - State: closed - Opened by newportchen 9 months ago - 1 comment
Labels: bug

#97 - RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

Issue - State: closed - Opened by jupinter 9 months ago - 1 comment
Labels: bug

#96 - Infer UI: Allow choose from common path.

Pull Request - State: closed - Opened by AnyaCoder 9 months ago

#95 - fix inference for FireflyGAN feature

Pull Request - State: closed - Opened by Stardust-minus 9 months ago

#94 - When to release vqgan-v2

Issue - State: closed - Opened by HaiFengZeng 9 months ago - 3 comments

#92 - LLAMA训练时长

Issue - State: closed - Opened by qiuyuzhao 9 months ago - 3 comments

#91 - Allow inplace transcripting. Fix some bugs. Add options.

Pull Request - State: closed - Opened by AnyaCoder 9 months ago

#90 - 训练报错[BUG]

Issue - State: closed - Opened by qiuyuzhao 9 months ago - 4 comments
Labels: bug

#89 - [BUG] Different code lead to different cloned audios.

Issue - State: closed - Opened by duj12 9 months ago - 1 comment
Labels: bug

#88 - Release V1

Pull Request - State: closed - Opened by leng-yue 9 months ago

#87 - [BUG]合成效果和网页上的效果不一样

Issue - State: closed - Opened by Zhou-Bolin 9 months ago - 2 comments
Labels: bug

#86 - [BUG] dockerfile

Issue - State: closed - Opened by qiuyuzhao 9 months ago - 5 comments
Labels: bug

#85 - 环境问题

Issue - State: closed - Opened by qiuyuzhao 9 months ago - 1 comment

#84 - undefined symbol

Issue - State: closed - Opened by qiuyuzhao 9 months ago - 7 comments

#83 - [BUG]中文很惊艳，英文完全不行的感觉

Issue - State: closed - Opened by jasonzhang761213 9 months ago - 4 comments
Labels: bug

#82 - [BUG]tone_sandhi相关

Issue - State: closed - Opened by KamioRinn 9 months ago - 1 comment
Labels: bug

#81 - [Feature]LLAMA 微调所需数据集的格式

Issue - State: closed - Opened by 12ben 9 months ago - 2 comments
Labels: enhancement

#80 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] 9 months ago

#78 - 📝(index): 前往预编译 flash-attn 包的指引

Pull Request - State: closed - Opened by HuanLinOTO 9 months ago

#77 - about base vq model and llm training dataset[Feature]

Issue - State: closed - Opened by forwiat 9 months ago - 1 comment
Labels: enhancement

#76 - Does this model support streaming？

Issue - State: closed - Opened by LCY-789456123 9 months ago - 1 comment
Labels: enhancement

#75 - Mel spec gen

Pull Request - State: closed - Opened by leng-yue 10 months ago

#74 - 偶发 Invalid argument的问题，出现在inference.py -i的环节

Issue - State: closed - Opened by go-mixed 10 months ago - 4 comments
Labels: bug

#73 - Merge update into dev

Pull Request - State: closed - Opened by leng-yue 10 months ago

#72 - 训练数据必须区分发音人吗？

Issue - State: closed - Opened by yy524 10 months ago - 1 comment
Labels: enhancement

#71 - [Add Feature] Make the whisper transcription better

Pull Request - State: closed - Opened by AnyaCoder 10 months ago

#70 - [Help] "pip install -e" fails

Issue - State: closed - Opened by APISeeker 10 months ago - 11 comments
Labels: help wanted

#69 - [Feature] how to start many data_server at the same time?

Issue - State: closed - Opened by Zth9730 10 months ago - 2 comments
Labels: enhancement

#67 - Optimize kui usage

Pull Request - State: closed - Opened by abersheeran 10 months ago

#66 - [BUG]生成的音频出现拼接问题

Issue - State: closed - Opened by hzfei 10 months ago - 1 comment
Labels: bug

#65 - [BUG] Hanging on train.py

Issue - State: closed - Opened by hzfei 10 months ago - 4 comments
Labels: bug

#62 - [QUESTION] VQGAN Low quality prediction for some audios

Issue - State: closed - Opened by TundraWork 10 months ago - 1 comment
Labels: bug

#61 - Training issue

Issue - State: closed - Opened by 443127316 10 months ago - 1 comment
Labels: enhancement

#60 - [Feature] 是否支持mps 芯片的训练？

Issue - State: closed - Opened by hsiunien 10 months ago - 3 comments
Labels: enhancement

#59 - [BUG] InstantiationException: Error locating target 'fish_speech.models.vqgan.VQGAN'

Issue - State: closed - Opened by gaotiesuanna 10 months ago - 9 comments
Labels: bug