DS_STORE #1266
Closed
DS_STORE #1266
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
使t2s模型支持批量推理: GPT_SoVITS/AR/models/t2s_model.py
修复batch bug GPT_SoVITS/AR/models/utils.py
重构的tts infer GPT_SoVITS/TTS_infer_pack/TTS.py
文本预处理模块 GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
new file GPT_SoVITS/TTS_infer_pack/__init__.py
文本拆分方法模块 GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py
tts infer配置文件 GPT_SoVITS/configs/tts_infer.yaml
modified GPT_SoVITS/feature_extractor/cnhubert.py
modified GPT_SoVITS/inference_gui.py
重构的webui GPT_SoVITS/inference_webui.py
new file GPT_SoVITS/inference_webui_old.py
添加音频倍速支持: GPT_SoVITS/inference_webui.py
…into rebuild-and-optimize
批量推理备份文件: GPT_SoVITS/AR/models/t2s_model_batch_only.py
增加一些新特性，并修复了一些bug GPT_SoVITS/TTS_infer_pack/TTS.py 优化网页布局 GPT_SoVITS/inference_webui.py
fixed some bugs GPT_SoVITS/TTS_infer_pack/TTS.py
tts infer重构优化和批量推理支持
…build-and-optimize
增加flash attention 选项: GPT_SoVITS/AR/models/t2s_model.py 增加flash attention 选项: GPT_SoVITS/TTS_infer_pack/TTS.py 增加flash attention 选项: GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py 增加flash attention 选项: GPT_SoVITS/configs/tts_infer.yaml 增加flash attention 选项: GPT_SoVITS/inference_webui.py
增加flash attention选项，防止影响训练
fix some bugs GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py fix some bugs GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py fix some bugs GPT_SoVITS/inference_webui.py fix some bugs GPT_SoVITS/module/models.py
新增VITS批量推理修复了一些bug
…oVITS-M into fast_inference_
优化了代码, 增加了健壮性
[fast_inference] 优化代码结构
Co-authored-by: starylan <[email protected]>
* 为fast_inference分支适配新的WebAPI * modified: api_v2.py * 修改文档细节 * modified: api_v2.py * 优化了代码逻辑，提升健壮性 * 修改文档细节 * 修改文档细节 * 优化代码逻辑 * 修改注释细节
* 添加with torch.no_grad()，速度快一大截 * 恢复先前缩进 * 恢复make batch的位置 * 改用修饰器 * 去除没必要的增加的空行 --------- Co-authored-by: XTer <[email protected]>
* Update README * Optimize-English-G2P * docs: change akward expression * docs: update Changelog_KO.md * Fix CN punc in EN,add 's match * Adjust normalize and g2p logic * Update zh_CN.json * Update README (RVC-Boss#827) Update README.md Update some outdated file paths and commands * 修复英文多音字,调整字典热加载,新增姓名匹配 (RVC-Boss#869) * Fix homograph dict * Add JSON in dict * Adjust hot dict to hot reload * Add English name dict * Adjust get name dict logic * Make API Great Again (RVC-Boss#894) * Add zh/jp/en mix * Optimize code readability and formatted output. * Try OGG streaming * Add stream mode arg * Add media type arg * Add cut punc arg * Eliminate punc risk * Update README (RVC-Boss#895) * Update README * Update README * update README * update README * fix typo s/Licence /License (RVC-Boss#904) * fix reformat cmd (RVC-Boss#917) Co-authored-by: starylan <[email protected]> * Update README.md * Normalize chinese arithmetic operations (RVC-Boss#947) * 改变训练和推理时的mask策略，以修复当batch_size>1时，产生的复读现象 * 同步main分支代码，增加“保持随机”选项 * 在colab中运行colab_webui.ipynb发生的uvr5模型缺失问题 (RVC-Boss#968) 在colab中使用git下载uvr5模型时报错： fatal: destination path 'uvr5_weights' already exists and is not an empty directory. 通过在下载前将原本从本仓库下载的uvr5_weights文件夹删除可以解决问题。 * [ASR] 修复FasterWhisper遍历输入路径失败 (RVC-Boss#956) * remove glob * rename * reset mirror pos * 回退mask策略； 回退pad策略； 在T2SBlock中添加padding_mask，以减少pad的影响； 开放repetition_penalty参数，让用户自行调整重复惩罚的强度； 增加parallel_infer参数，用于开启或关闭并行推理，关闭时与0307版本保持一致； 在webui中增加“保持随机”选项； 同步main分支代码。 * 删除无用注释 --------- Co-authored-by: Lion <[email protected]> Co-authored-by: RVC-Boss <[email protected]> Co-authored-by: KamioRinn <[email protected]> Co-authored-by: Pengoose <[email protected]> Co-authored-by: Yuan-Man <[email protected]> Co-authored-by: XXXXRT666 <[email protected]> Co-authored-by: KamioRinn <[email protected]> Co-authored-by: Lion-Wu <[email protected]> Co-authored-by: digger yu <[email protected]> Co-authored-by: SapphireLab <[email protected]> Co-authored-by: starylan <[email protected]> Co-authored-by: shadow01a <[email protected]>
…ce speed when exchange model weights (RVC-Boss#1058) * chore: add the ability of lru cache for api v3 to improve the inference speed when exchange model weights * chore: Dockerfile start api v3 * chore: api default port from 127.0.0.1 to 0.0.0.0 * chore: make gpu happy when do tts * chore: rollback Dockerfile * chore: fix * chore: fix --------- Co-authored-by: kevin.zhang <[email protected]>
* api接口，修复文本切分符号设定中，中文分号错写为英文分号的问题 (RVC-Boss#1001) * 一些小问题修复 (RVC-Boss#1021) * fix import error. It may happen when calling api.py * Update README.md * Update gpt-sovits_kaggle.ipynb * Update gpt-sovits_kaggle.ipynb * fix path error delete useless line wraps * 删除重复的 COPY 指令 (RVC-Boss#1073) * [优化] 1Aa-文本获取 (RVC-Boss#1102) * Filter unsupported languages * add feedback * simplify modification * fix detail * Update english.py (RVC-Boss#1106) copy but not ref the phones list becoz it will be extend later, if not do so,it will affect the self.cmu dict values. * Update models.py * modify freeze_quantizer mode, avoid quantizer's codebook updating (RVC-Boss#953) --------- Co-authored-by: FengQingYunDan <[email protected]> Co-authored-by: Kenn Zhang <[email protected]> Co-authored-by: 蓝梦实 <[email protected]> Co-authored-by: lyris <[email protected]> Co-authored-by: hcwu1993 <[email protected]>
* Add files via upload (RVC-Boss#978) * Update api.py (RVC-Boss#979) 修复SynthesizerTrn kwargs 传递异常。 --------- Co-authored-by: Enes Çakırcalı <[email protected]> Co-authored-by: Hayo <[email protected]>
* punctuation * update * update
* Update TextPreprocessor.py * fix: 修复参考音频泄露的问题。 1. 之前变量命名有错误 2. 还存在参考音频泄露问题。 * 调整一下判断纯符号所处的函数，更符号逻辑
…_audio的bug【首次音频帧从3.2s -> 1.7s】 (RVC-Boss#1235)
在推理完成之后，使用gc控制器对内存进行回收。 RVC-Boss#1218
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
#1265