lenML/Speech-AI-Forge issues and pull requests

#194 - API Demo Examples

Issue - State: open - Opened by zhzLuke96 2 days ago
Labels: documentation, Story

#193 - [ISSUE] Failed to build installable wheels for some pyproject.toml based projects (pynini)

Issue - State: open - Opened by Jianing163 9 days ago - 11 comments
Labels: question, dependencies, env

#192 - Fix pipeline performance

Issue - State: open - Opened by zhzLuke96 19 days ago
Labels: Story, performance

#191 - Support FishSpeech1.4

Issue - State: open - Opened by zhzLuke96 21 days ago
Labels: Story

#189 - improve SPK file

Issue - State: open - Opened by zhzLuke96 23 days ago
Labels: Story

#188 - [BUG:API] chat_tts模块缺少内容

Issue - State: open - Opened by jcorgdev 23 days ago - 1 comment
Labels: bug

#187 - 全功能异步接口 `v2/*`

Issue - State: open - Opened by zhzLuke96 24 days ago
Labels: Story

#186 - [ISSUE] No module named 'tools.file'

Issue - State: open - Opened by ahkimkoo 26 days ago - 2 comments
Labels: bug, upstream

#185 - [BUG:WebUI] 解决由于huggingface_hub版本问题导致的运行不起来。

Issue - State: closed - Opened by ChaoliesTinnu about 1 month ago - 1 comment
Labels: bug

#184 - 我发现会越说越快，不知道是不是正常的？

Issue - State: closed - Opened by gg22mm about 1 month ago - 1 comment
Labels: question

#183 - Support Pinyin Customization for F5-TTS

Issue - State: closed - Opened by zhzLuke96 about 1 month ago - 3 comments
Labels: Story

#182 - [Feature] 请问是否可以支持多音字声调修正

Issue - State: closed - Opened by andywu188 about 1 month ago - 2 comments
Labels: enhancement

#181 - [BUG:WebUI]

Issue - State: closed - Opened by xiaoliu66 about 1 month ago - 2 comments
Labels: bug

#180 - [ISSUE] F5TTS 推理显示RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

Issue - State: closed - Opened by dhlsam about 1 month ago - 1 comment
Labels: bug

#179 - [BUG] Colab not working

Issue - State: closed - Opened by zhzLuke96 about 1 month ago - 1 comment
Labels: bug

#178 - [BUG] 在 windows 环境，FireRedTTS tn 报错

Issue - State: closed - Opened by zhzLuke96 about 2 months ago - 1 comment
Labels: enhancement

#177 - F5-TTS inpainting

Issue - State: open - Opened by zhzLuke96 about 2 months ago
Labels: Story

#176 - Support F5-TTS

Issue - State: closed - Opened by zhzLuke96 about 2 months ago - 1 comment
Labels: Story

#175 - 完善 ModelZoo

Issue - State: open - Opened by zhzLuke96 about 2 months ago - 1 comment
Labels: Story

#174 - Update README.md

Pull Request - State: closed - Opened by xxyyboy about 2 months ago - 1 comment

#173 - [ISSUE] API调用流式输出等待后台编译完才传输

Issue - State: closed - Opened by xhjcxxl about 2 months ago - 4 comments
Labels: question

#171 - 支持调整编码器配置

Issue - State: closed - Opened by zhzLuke96 about 2 months ago - 1 comment
Labels: Story

#170 - [ISSUE] api接口下流式输出处理

Issue - State: closed - Opened by xhjcxxl about 2 months ago - 4 comments
Labels: question

#169 - [ISSUE] 通过--device_id指定GPU设备对除ChatTTS外模型无效

Issue - State: closed - Opened by Seayar about 2 months ago - 3 comments
Labels: bug, quick_fix

#168 - [BUG:WebUI]

Issue - State: open - Opened by kuhubmk about 2 months ago - 3 comments
Labels: bug

#167 - WebUI: improve SSML tools

Issue - State: closed - Opened by zhzLuke96 about 2 months ago - 1 comment
Labels: Story

#166 - 增加部分文字中文翻译

Pull Request - State: closed - Opened by andywu188 about 2 months ago - 1 comment

#165 - Support FireRedTTS

Issue - State: closed - Opened by zhzLuke96 about 2 months ago - 3 comments
Labels: Story

#163 - [Feature] 界面上增加一个生成音频格式选择功能

Issue - State: open - Opened by andywu188 about 2 months ago - 3 comments
Labels: enhancement

#162 - [ISSUE] 语音复刻出现问题，提示：Could not initialize NNPACK! Reason: Unsupported hardware

Issue - State: open - Opened by No-22-Github about 2 months ago - 2 comments

#161 - [ISSUE] the docker config is broken

Issue - State: closed - Opened by highkay 2 months ago - 1 comment
Labels: bug

#160 - [BUG:FT] 选择说话风格后，文本会生成不完全，会少最后几句。

Issue - State: open - Opened by wangqun888 2 months ago - 3 comments
Labels: bug

#158 - [BUG:WebUI] 上传参考音频输出的音色不匹配并且全是杂音，前摇也很长

Issue - State: closed - Opened by nulinuli 2 months ago - 3 comments
Labels: bug

#157 - [ISSUE] 无法使用GPU来运行

Issue - State: closed - Opened by kyrosin 2 months ago - 4 comments

#154 - [BUG:WebUI] 点击Web页面上的“生成单频”按钮后报错

Issue - State: open - Opened by haijd 3 months ago - 6 comments
Labels: bug

#153 - [Bug] chattts使用随机种子生成音色报错

Issue - State: closed - Opened by zydmtaichi 3 months ago - 6 comments

#152 - [BUG] SSML duration/prosody 生成结果不对

Issue - State: closed - Opened by zhzLuke96 3 months ago - 1 comment
Labels: bug

#150 - [ISSUE] cuda11.6下部署该项目发生循环扫描torch版本，无法安装成功

Issue - State: closed - Opened by zydmtaichi 3 months ago - 1 comment

#148 - [BUG:API] 文本转语音无报错，但非常的慢，超过120S

Issue - State: closed - Opened by Ccccx 3 months ago - 1 comment
Labels: bug, performance

#147 - [BUG:API] 上传Speaker接口，使用tensor来创建音色并且传入了name、gender、describe但是没有写入spkv1.json文件中

Issue - State: open - Opened by coutlinx 3 months ago - 1 comment
Labels: bug, enhancement

#146 - [ISSUE] 人声增强与背景降噪

Issue - State: closed - Opened by cpken 3 months ago

#145 - [ISSUE] 如何应用韵律apply_prosody

Issue - State: closed - Opened by cpken 3 months ago

#144 - [BUG:FT] cosyvoice 生成音频报错

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

#143 - [BUG:API] 部署到HF Space 调用接口报错 RuntimeError: CUDA must not be initialized in the main process on Spaces with Stateless GPU environment.

Issue - State: closed - Opened by steveoon 3 months ago - 5 comments
Labels: bug, delayed

#142 - [BUG:FT] AttributeError: 'Chat' object has no attribute 'gpt'

Issue - State: closed - Opened by cpken 3 months ago - 1 comment
Labels: question

#141 - [assistance] Confirmation on Data Format and Structure for Fine-Tuning

Issue - State: open - Opened by IrisSally 3 months ago - 2 comments

#140 - [Feature] Support customized models path

Issue - State: open - Opened by kerol123 3 months ago - 2 comments
Labels: enhancement

#139 - [BUG:WebUI] ASR 操作报错 Error: libcudnn_ops_infer.so.8

Issue - State: closed - Opened by cpken 4 months ago - 2 comments
Labels: question, env

#138 - [BUG:API] stream流式api特别慢

Issue - State: closed - Opened by xiaozhu1106 4 months ago - 2 comments
Labels: bug, quick_fix, performance

#137 - [ISSUE] ImportError: cannot import name 'AudioNormalizer' from partially initialized module 'modules.core.pipeline.factory' (most likely due to a circular import) (/data/chattts-forge/modules/core/pipeline/factory.py)

Issue - State: closed - Opened by shawnwu2022 4 months ago - 1 comment
Labels: bug

#136 - replace chattts modelscope_repo with AI-ModelScope

Pull Request - State: closed - Opened by fangd123 4 months ago - 1 comment

#135 - Support FishSpeech SFT version

Issue - State: closed - Opened by zhzLuke96 4 months ago - 2 comments
Labels: Story

#134 - [BUG:API] /v1/tts 使用--compile后加载fishspeech卡死

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

#133 - [BUG:WebUI] 生成的spk和参考音频不符

Issue - State: closed - Opened by tuxiaoseng 4 months ago - 5 comments
Labels: bug, upstream, MF

#132 - [BUG:API] /v1/ssml

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

#131 - Improve WebUI 0.8

Issue - State: closed - Opened by zhzLuke96 4 months ago - 1 comment
Labels: Story

#130 - [Feature] Examples of Cloning Audio and Text with One-Shot TTS and Streaming Output

Issue - State: closed - Opened by IrisSally 4 months ago - 4 comments
Labels: enhancement, Story

#129 - window 使用错误[ISSUE]

Issue - State: closed - Opened by wtjwrold 4 months ago - 1 comment

#127 - [BUG:WebUI]

Issue - State: closed - Opened by 2open1024 4 months ago - 1 comment
Labels: question, quick_fix

#126 - [BUG:WebUI] Error: AttributeError: '_io.BufferedRandom' object has no attribute 'endswith'

Issue - State: closed - Opened by 2open1024 4 months ago - 1 comment
Labels: question, quick_fix

#124 - [ISSUE] API请求无法并行处理多个，服务器端总是一个处理完才处理下一个

Issue - State: open - Opened by zsy-code 4 months ago - 4 comments

#123 - ASR WebUI

Issue - State: closed - Opened by zhzLuke96 4 months ago - 1 comment
Labels: Story

#122 - support SenseVoice

Issue - State: open - Opened by zhzLuke96 4 months ago
Labels: Story

#121 - ChatTTS emb finetune with `DVAE_full.pt`

Issue - State: open - Opened by zhzLuke96 4 months ago - 7 comments
Labels: enhancement, Story

#120 - [BUG:API] /prompt/refine接口异常

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

#119 - [ISSUE] 在M芯片的MacBook上报错：RuntimeError: Placeholder storage has not been allocated on MPS device!

Issue - State: open - Opened by atfa 4 months ago - 1 comment
Labels: help wanted

#117 - [ISSUE] 优化文本产生乱码

Issue - State: closed - Opened by ahkimkoo 4 months ago - 2 comments

#116 - [BUG:API] /prompt/refine接口异常

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

#115 - fix: topK and topP not valid

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

#114 - [BUG:API] 使用/v1/speaker/create创建了一个spaker，调用/v1/audio/speech接口时报错

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

#113 - [Plan] support ChatTTS zero shot infer

Issue - State: closed - Opened by zhzLuke96 4 months ago - 3 comments
Labels: enhancement, Story, upstream

#112 - [Plan] Add vLLM Wrapper

Issue - State: open - Opened by zhzLuke96 4 months ago - 3 comments
Labels: enhancement, Story, upstream, delayed

#111 - Support for One-Shot Voice Cloning and vLLM Integration in ChatTTS-Forge

Issue - State: closed - Opened by IrisSally 4 months ago - 5 comments
Labels: enhancement, upstream

#110 - [ISSUE] 关于开启--compile之后，webui输出窗口乱码以及api后台卡主

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

#109 - tts_stream的返回结果实现流式返回[ISSUE]

Issue - State: closed - Opened by panpan123456 4 months ago - 3 comments

#108 - linux tts_stream返回结果为空[BUG:API]

Issue - State: closed - Opened by panpan123456 5 months ago - 1 comment
Labels: bug

#107 - RuntimeError: expected scalar type ComplexDouble but found ComplexHalf[BUG:API]

Issue - State: closed - Opened by panpan123456 5 months ago - 2 comments
Labels: bug

#106 - ValueError: mutable default <class 'modules.core.handler.datacls.chattts_model.ChatTTSConfig'> for field tts_config is not allowed: use default_factory[BUG:API]

Issue - State: closed - Opened by panpan123456 5 months ago - 1 comment
Labels: bug

#105 - [BUG:WebUI] 无法使用说话人种子生成语音

Issue - State: closed - Opened by OrvilleQ 5 months ago - 1 comment
Labels: bug

#104 - [Plan] Speaker Card file (PNG embed)

Issue - State: closed - Opened by zhzLuke96 5 months ago - 1 comment
Labels: Story, Deprecated

#103 - [BUG:API] 降噪参数开启后，声音不对了

Issue - State: closed - Opened by tuxiaoseng 5 months ago - 4 comments
Labels: bug

#102 - Dev tts pipeline

Pull Request - State: closed - Opened by zhzLuke96 5 months ago
Labels: enhancement, breaking

#101 - [Plan] add support RVC

Issue - State: open - Opened by zhzLuke96 5 months ago
Labels: enhancement, Story

#100 - [Plan] add support OpenVoice

Issue - State: closed - Opened by zhzLuke96 5 months ago - 3 comments
Labels: enhancement, Story

#99 - [BUG:API] api生成语音时不时出现错误，导致内存溢出

Issue - State: open - Opened by tuxiaoseng 5 months ago - 6 comments
Labels: bug, quick_fix, upstream

#98 - 流式输出声音有杂音[ISSUE]

Issue - State: open - Opened by huai-ying 5 months ago - 5 comments
Labels: bug, quick_fix, upstream

#97 - [ISSUE] flash_attn f16 warning

Issue - State: open - Opened by zhzLuke96 5 months ago
Labels: bug, help wanted, upstream

#96 - 如何提高生成语音的速度？

Issue - State: open - Opened by caixianyu 5 months ago - 3 comments
Labels: help wanted, question, upstream

#95 - 我使用web ui通过mmsl生成语音时，发现示例中的[BUG:WebUI] <speak version="0.1"> <voice spk="Bob" seed="42" style="narration-relaxed"> 使用 break 标签将会简单的 [lbreak] <break time="500" /> 插入一段空白到生成结果中 [lbreak] </voice> </speak>转换时会出现错误。

Issue - State: closed - Opened by Zuo-Cheng 5 months ago - 1 comment
Labels: bug

GitHub / lenML/Speech-AI-Forge issues and pull requests