Shiina-Mahiru/Firefly-Neko

By Shiina-Mahiru · ↓ 0 · ♥ 5 · Updated 2025-02-25

What's in this repo

This page lists the files in Shiina-Mahiru/Firefly-Neko, including tools\uvr5\uvr5_weights\onnx_dereverb_By_FoxJoy\vocals.onnx.

1 ONNX models (.onnx files)
267 files, including 77 .json, 52 .py, 27 .pyc, 10 .pth, 10 .txt, 9 .png
Last updated 2025-02-25

ONNX files

File	Size	Download
tools\uvr5\uvr5_weights\onnx_dereverb_By_FoxJoy\vocals.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Firefly-Neko流萤猫酱

🤗完整资源文件夹压缩包(旧版，未增加历史记录功能)

项目简介

Firefly-Neko 是一个集成了live2d模型、语音转文字（STT）和大语言模型（LLM）处理的项目。该项目使用 PyTorch 和 Transformers 等库，通过并行处理实现实时语音转文字和文本生成。正如名字所见，本项目构建了一个流萤猫酱的形象。

功能

实时语音转文字（STT）（使用FunASR）
文本生成和修正（LLM）（使用Qwen2.5-7B-Instruct模型）
并行处理 STT 和 LLM 任务
自动播放生成的语音文件（使用GPT-SoVITS，流萤语音模型使用的是b站白菜工厂1145号员工大佬的GPT-SoVITS模型，🤗Hugging Face地址）
具有live2d模型（使用是b站依七哒大佬的流萤前瞻小人模型)
live2d可交互，可以点击头部、脸部、脚部、手部，还有欧派😋
新增历史记录功能

使用方法

下载仓库内所有内容；
下载到本地后先将GPT-SoVITS-v2-240821.zip解压；
然后在该目录下输入pip install -r requirements.txt安装依赖，其中一些模块的下载需要依赖Microsoft Visual Studio，可下载vs然后选择“C/C++桌面开发”安装完后再用pip下载这些模块就不会build wheels error了；
接着直接运行firefly-neko-live2d.py即可。

注意事项

请确保在运行脚本前，所有依赖项和模型文件已正确安装和配置。
如果在运行过程中遇到任何问题，请检查依赖项版本和模型文件路径是否正确。
本仓库适用于开源学习、娱乐目的，在询问模型作者许可后方可用于商业用途，若使用者触犯法律以及危害模型作者的权益，本仓库概不负责。

贡献

欢迎在community中讨论来改进本项目。

Model info

audio-text-to-text

onnx safetensors audio-text-to-text base_model:Qwen/Qwen2.5-7B-Instruct-1M base_model:quantized:Qwen/Qwen2.5-7B-Instruct-1M license:mit region:us

↓ 0 ♥ 5

Created: 2025-02-06

Updated: 2025-02-25

View on Hugging Face

Files (267)

.gitattributes

Firefly-desktop\Firefly.4096\texture_00.png

Firefly-desktop\Firefly.cdi3.json

Firefly-desktop\Firefly.moc3

Firefly-desktop\Firefly.model3.json

Firefly-desktop\Firefly.physics3.json

Firefly-desktop\animations\Scene0.motion3.json

Firefly-desktop\animations\Scene02.motion3.json

Firefly-desktop\animations\Scene22.motion3.json

Firefly-desktop\animations\Scene26710.motion3.json

Firefly-desktop\animations\Scene4.motion3.json

Firefly-desktop\expression\expression1.exp3.json

Firefly-desktop\expression\expression2.exp3.json

Firefly-desktop\expression\expression3.exp3.json

Firefly-desktop\voice\meow.mp3

Firefly-desktop\voice\会萤的.mp3

Firefly-desktop\voice\无梦-若风 - 使一颗心免于哀伤-流萤.mp3

Firefly-desktop\voice\音频回正.mp3

GPT-SoVITS-v2-240821.7z

GPT_SoVITS\pretrained_models\.gitignore

GPT_SoVITS\pretrained_models\chinese-hubert-base\config.json

GPT_SoVITS\pretrained_models\chinese-hubert-base\preprocessor_config.json

GPT_SoVITS\pretrained_models\chinese-hubert-base\pytorch_model.bin

GPT_SoVITS\pretrained_models\chinese-roberta-wwm-ext-large\config.json

GPT_SoVITS\pretrained_models\chinese-roberta-wwm-ext-large\pytorch_model.bin

GPT_SoVITS\pretrained_models\chinese-roberta-wwm-ext-large\tokenizer.json

GPT_SoVITS\pretrained_models\gsv-v2final-pretrained\s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt

GPT_SoVITS\pretrained_models\gsv-v2final-pretrained\s2D2333k.pth

GPT_SoVITS\pretrained_models\gsv-v2final-pretrained\s2G2333k.pth

GPT_SoVITS\pretrained_models\s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt

GPT_SoVITS\pretrained_models\s2D488k.pth

GPT_SoVITS\pretrained_models\s2G488k.pth

GPT_weights_v2\流萤-e10.ckpt

README.md

SoVITS_weights_v2\流萤_e15_s810.pth

__pycache__\jieba_fast_functions_py3.cpython-312.pyc

__pycache__\qwen_firefly_neko_stt_multi.cpython-312.pyc

background.txt

dialog_history.json

example.wav

ffmpeg.exe

ffmpeg\__init__.py

ffmpeg\__pycache__\__init__.cpython-312.pyc

ffmpeg\__pycache__\__init__.cpython-39.pyc

ffmpeg\__pycache__\_ffmpeg.cpython-312.pyc

ffmpeg\__pycache__\_ffmpeg.cpython-39.pyc

ffmpeg\__pycache__\_filters.cpython-312.pyc

ffmpeg\__pycache__\_filters.cpython-39.pyc

ffmpeg\__pycache__\_probe.cpython-312.pyc

ffmpeg\__pycache__\_probe.cpython-39.pyc

ffmpeg\__pycache__\_run.cpython-312.pyc

ffmpeg\__pycache__\_run.cpython-39.pyc

ffmpeg\__pycache__\_utils.cpython-312.pyc

ffmpeg\__pycache__\_utils.cpython-39.pyc

ffmpeg\__pycache__\_view.cpython-312.pyc

ffmpeg\__pycache__\_view.cpython-39.pyc

ffmpeg\__pycache__\dag.cpython-312.pyc

ffmpeg\__pycache__\dag.cpython-39.pyc

ffmpeg\__pycache__\nodes.cpython-312.pyc

ffmpeg\__pycache__\nodes.cpython-39.pyc

ffmpeg\_ffmpeg.py

ffmpeg\_filters.py

ffmpeg\_probe.py

ffmpeg\_run.py

ffmpeg\_utils.py

ffmpeg\_view.py

ffmpeg\dag.py

ffmpeg\nodes.py

ffprobe.exe

firefly-neko-live2d.py

firefly-neko-stt-live2d-multi.py

firefly-neko-stt-multi.py

firefly-neko-stt.py

firefly-neko-txt.py

firefly\ref_audio\example.wav

model\Qwen2.5-0.5B-Instruct\config.json

model\Qwen2.5-0.5B-Instruct\generation_config.json

model\Qwen2.5-0.5B-Instruct\merges.txt

model\Qwen2.5-0.5B-Instruct\model.safetensors

model\Qwen2.5-0.5B-Instruct\tokenizer.json

model\Qwen2.5-0.5B-Instruct\tokenizer_config.json

model\Qwen2.5-0.5B-Instruct\vocab.json

model\Qwen2.5-7B-Instruct\config.json

model\Qwen2.5-7B-Instruct\generation_config.json

model\Qwen2.5-7B-Instruct\merges.txt

model\Qwen2.5-7B-Instruct\model-00001-of-00004.safetensors

model\Qwen2.5-7B-Instruct\model-00002-of-00004.safetensors

model\Qwen2.5-7B-Instruct\model-00003-of-00004.safetensors

model\Qwen2.5-7B-Instruct\model-00004-of-00004.safetensors

model\Qwen2.5-7B-Instruct\model.safetensors.index.json

model\Qwen2.5-7B-Instruct\tokenizer.json

model\Qwen2.5-7B-Instruct\tokenizer_config.json

model\Qwen2.5-7B-Instruct\vocab.json

model\punc_ct-transformer_cn-en-common-vocab471067-large\.mdl

model\punc_ct-transformer_cn-en-common-vocab471067-large\.msc

model\punc_ct-transformer_cn-en-common-vocab471067-large\.mv

model\punc_ct-transformer_cn-en-common-vocab471067-large\README.md

model\punc_ct-transformer_cn-en-common-vocab471067-large\config.yaml

model\punc_ct-transformer_cn-en-common-vocab471067-large\configuration.json

model\punc_ct-transformer_cn-en-common-vocab471067-large\example\punc_example.txt

model\punc_ct-transformer_cn-en-common-vocab471067-large\fig\struct.png

model\punc_ct-transformer_cn-en-common-vocab471067-large\jieba.c.dict

model\punc_ct-transformer_cn-en-common-vocab471067-large\jieba_usr_dict

model\punc_ct-transformer_cn-en-common-vocab471067-large\model.pt

model\punc_ct-transformer_cn-en-common-vocab471067-large\tokens.json

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\.DS_Store

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\.mdl

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\.msc

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\README.md

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\config.yaml

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\configuration.json

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\example\punc_example.txt

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\fig\struct.png

model\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\tokens.json

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\.mdl

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\.msc

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\.mv

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\README.md

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\am.mvn

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\config.yaml

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\configuration.json

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\example\vad_example.wav

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\fig\struct.png

model\speech_fsmn_vad_zh-cn-16k-common-pytorch\model.pt

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\.mdl

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\.msc

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\.mv

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\README.md

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\am.mvn

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\asr_example_hotword.wav

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\config.yaml

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\configuration.json

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\example\asr_example.wav

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\example\hotword.txt

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\fig\res.png

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\fig\seaco.png

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\model.pt

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\seg_dict

model\speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\tokens.json

output\output.wav

readme.md

ref_text.txt

requirements.txt

target_text.txt

tools\__init__.py

tools\__pycache__\__init__.cpython-312.pyc

tools\__pycache__\__init__.cpython-39.pyc

tools\__pycache__\my_utils.cpython-312.pyc

tools\__pycache__\my_utils.cpython-39.pyc

tools\asr\__pycache__\config.cpython-39.pyc

tools\asr\config.py

tools\asr\fasterwhisper_asr.py

tools\asr\funasr_asr.py

tools\asr\models\.gitignore

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\.DS_Store

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\.mdl

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\.msc

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\README.md

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\config.yaml

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\configuration.json

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\example\punc_example.txt

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\fig\struct.png

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\model.pt

tools\asr\models\punc_ct-transformer_zh-cn-common-vocab272727-pytorch\tokens.json

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\.mdl

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\.msc

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\README.md

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\am.mvn

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\config.yaml

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\configuration.json

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\example\vad_example.wav

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\fig\struct.png

tools\asr\models\speech_fsmn_vad_zh-cn-16k-common-pytorch\model.pt

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\.mdl

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\.msc

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\README.md

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\am.mvn

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\config.yaml

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\configuration.json

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\example\asr_example.wav

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\fig\struct.png

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\model.pt

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\seg_dict

tools\asr\models\speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch\tokens.json

tools\cmd-denoise.py

tools\denoise-model\.gitignore

tools\i18n\__pycache__\i18n.cpython-312.pyc

tools\i18n\__pycache__\i18n.cpython-39.pyc

tools\i18n\i18n.py

tools\i18n\locale\en_US.json

tools\i18n\locale\es_ES.json

tools\i18n\locale\fr_FR.json

tools\i18n\locale\it_IT.json

tools\i18n\locale\ja_JP.json

tools\i18n\locale\ko_KR.json

tools\i18n\locale\pt_BR.json

tools\i18n\locale\ru_RU.json

tools\i18n\locale\tr_TR.json

tools\i18n\locale\zh_CN.json

tools\i18n\locale\zh_HK.json

tools\i18n\locale\zh_SG.json

tools\i18n\locale\zh_TW.json

tools\i18n\locale_diff.py

tools\i18n\scan_i18n.py

tools\my_utils.py

tools\slice_audio.py

tools\slicer2.py

tools\subfix_webui.py

tools\uvr5\bs_roformer\__init__.py

tools\uvr5\bs_roformer\attend.py

tools\uvr5\bs_roformer\bs_roformer.py

tools\uvr5\bsroformer.py

tools\uvr5\lib\lib_v5\dataset.py

tools\uvr5\lib\lib_v5\layers.py

tools\uvr5\lib\lib_v5\layers_123812KB.py

tools\uvr5\lib\lib_v5\layers_123821KB.py

tools\uvr5\lib\lib_v5\layers_33966KB.py

tools\uvr5\lib\lib_v5\layers_537227KB.py

tools\uvr5\lib\lib_v5\layers_537238KB.py

tools\uvr5\lib\lib_v5\layers_new.py

tools\uvr5\lib\lib_v5\model_param_init.py

tools\uvr5\lib\lib_v5\modelparams\1band_sr16000_hl512.json

tools\uvr5\lib\lib_v5\modelparams\1band_sr32000_hl512.json

tools\uvr5\lib\lib_v5\modelparams\1band_sr33075_hl384.json

tools\uvr5\lib\lib_v5\modelparams\1band_sr44100_hl1024.json

tools\uvr5\lib\lib_v5\modelparams\1band_sr44100_hl256.json

tools\uvr5\lib\lib_v5\modelparams\1band_sr44100_hl512.json

tools\uvr5\lib\lib_v5\modelparams\1band_sr44100_hl512_cut.json

tools\uvr5\lib\lib_v5\modelparams\2band_32000.json

tools\uvr5\lib\lib_v5\modelparams\2band_44100_lofi.json

tools\uvr5\lib\lib_v5\modelparams\2band_48000.json

tools\uvr5\lib\lib_v5\modelparams\3band_44100.json

tools\uvr5\lib\lib_v5\modelparams\3band_44100_mid.json

tools\uvr5\lib\lib_v5\modelparams\3band_44100_msb2.json

tools\uvr5\lib\lib_v5\modelparams\4band_44100.json

tools\uvr5\lib\lib_v5\modelparams\4band_44100_mid.json

tools\uvr5\lib\lib_v5\modelparams\4band_44100_msb.json

tools\uvr5\lib\lib_v5\modelparams\4band_44100_msb2.json

tools\uvr5\lib\lib_v5\modelparams\4band_44100_reverse.json

tools\uvr5\lib\lib_v5\modelparams\4band_44100_sw.json

tools\uvr5\lib\lib_v5\modelparams\4band_v2.json

tools\uvr5\lib\lib_v5\modelparams\4band_v2_sn.json

tools\uvr5\lib\lib_v5\modelparams\4band_v3.json

tools\uvr5\lib\lib_v5\modelparams\ensemble.json

tools\uvr5\lib\lib_v5\nets.py

tools\uvr5\lib\lib_v5\nets_123812KB.py

tools\uvr5\lib\lib_v5\nets_123821KB.py

tools\uvr5\lib\lib_v5\nets_33966KB.py

tools\uvr5\lib\lib_v5\nets_537227KB.py

tools\uvr5\lib\lib_v5\nets_537238KB.py

tools\uvr5\lib\lib_v5\nets_61968KB.py

tools\uvr5\lib\lib_v5\nets_new.py

tools\uvr5\lib\lib_v5\spec_utils.py

tools\uvr5\lib\name_params.json

tools\uvr5\lib\utils.py

tools\uvr5\mdxnet.py

tools\uvr5\uvr5_weights\.gitignore

tools\uvr5\uvr5_weights\HP2_all_vocals.pth

tools\uvr5\uvr5_weights\HP5_only_main_vocal.pth

tools\uvr5\uvr5_weights\VR-DeEchoAggressive.pth

tools\uvr5\uvr5_weights\VR-DeEchoDeReverb.pth

tools\uvr5\uvr5_weights\VR-DeEchoNormal.pth

tools\uvr5\uvr5_weights\model_bs_roformer_ep_317_sdr_12.9755.ckpt

tools\uvr5\uvr5_weights\onnx_dereverb_By_FoxJoy\vocals.onnx ONNX

tools\uvr5\vr.py

tools\uvr5\webui.py

weight.json

Related models

More from Shiina-Mahiru

No other models by this author.

More audio-text-to-text models

Browse all audio-text-to-text models