-
Notifications
You must be signed in to change notification settings - Fork 495
Insights: FunAudioLLM/CosyVoice
September 13, 2024 – September 20, 2024
Overview
Could not load contribution data
Please try again later
6 Pull requests merged by 4 people
-
Dev/lyuxiang.lx
#408 merged
Sep 19, 2024 -
[debug] fix badcase, add fade on speech output
#379 merged
Sep 19, 2024 -
Dev/lyuxiang.lx
#404 merged
Sep 18, 2024 -
Implemented fast processing of extract_embedding
#356 merged
Sep 18, 2024 -
update tempo change
#403 merged
Sep 18, 2024 -
Add dockerfile for python 3.8, cuda 11.8 and torch 2.0.1 version
#378 merged
Sep 18, 2024
1 Pull request opened by 1 person
-
[debug] support flow cache, for sharper tts_mel output
#412 opened
Sep 20, 2024
4 Issues closed by 4 people
-
非常棒的项目,想问一下都支持什么情绪和语气呀?
#119 closed
Sep 20, 2024 -
【bug】temperature的随机性导致流式推理前后窗的mel谱不连续
#406 closed
Sep 20, 2024 -
[Help] Question about the implementation of MaskedDiffWithXvec.
#407 closed
Sep 19, 2024 -
Checkpoints for LibriTTS experiments from paper?
#405 closed
Sep 19, 2024
12 Issues opened by 12 people
-
extract_embedding.py报segmentation default错误。
#415 opened
Sep 20, 2024 -
ampplus.onnx failed. File doesn't exist
#414 opened
Sep 20, 2024 -
4096维的speech_token具体是哪些?能否提供token样例?
#413 opened
Sep 20, 2024 -
用其他语种作为prompt_speech_16k进行声音克隆无法实现跨语种
#411 opened
Sep 20, 2024 -
About instant-feature-extraction training
#409 opened
Sep 20, 2024 -
0915下载cosyvoice版本,生成音频无法下载
#402 opened
Sep 15, 2024 -
Mac端直接点击生成语音报错
#401 opened
Sep 15, 2024 -
sft 中文男 声音突然会变小
#400 opened
Sep 14, 2024 -
Failed to export onnx model from flow
#399 opened
Sep 14, 2024 -
点击生成音频报错:Connection Error out?连接失败?
#398 opened
Sep 14, 2024 -
当用循环生成语音时超过三条文本就会出现错误
#397 opened
Sep 14, 2024 -
instruct_text应该如何设置
#396 opened
Sep 14, 2024
29 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
Training Problem
#275 commented on
Sep 14, 2024 • 0 new comments -
ImportError: There is no such entity as whisper.tokenizer.get_tokenizer
#251 commented on
Sep 14, 2024 • 0 new comments -
按照文档运行测试程序时报错:ImportError: There is no such entity as whisper.tokenizer.get_tokenizer
#203 commented on
Sep 14, 2024 • 0 new comments -
跨语种复制模式下从日语到中文会出现粤语输出 Cantonese output appears from Japanese to Chinese in cross-language copying mode
#385 commented on
Sep 14, 2024 • 0 new comments -
中文转日文音频
#390 commented on
Sep 14, 2024 • 0 new comments -
安装的时候为什么会出现campplus.onnx错误啊?
#395 commented on
Sep 14, 2024 • 0 new comments -
probability tensor contains either `inf`, `nan` or element < 0
#393 commented on
Sep 14, 2024 • 0 new comments -
Try to train llm model with cosyvoice.fromscratch.yaml. The loss is not converging.
#391 commented on
Sep 14, 2024 • 0 new comments -
采用语音复刻推理,相同文本结果都不同
#394 commented on
Sep 14, 2024 • 0 new comments -
About the training of the flow model
#308 commented on
Sep 14, 2024 • 0 new comments -
生成的语音有时候会出现重复读某一句
#290 commented on
Sep 15, 2024 • 0 new comments -
Information on training dataset and duration for CosyVoice-300M
#285 commented on
Sep 15, 2024 • 0 new comments -
Restart training from a checkpoint, with steps, etc
#282 commented on
Sep 15, 2024 • 0 new comments -
语音生成效率低
#287 commented on
Sep 16, 2024 • 0 new comments -
flow matching训练的pipeline?
#281 commented on
Sep 16, 2024 • 0 new comments -
安装 pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl 报错
#266 commented on
Sep 17, 2024 • 0 new comments -
Uneven dataset loaded to GPUs can cause ranks failed especially in the DDP mode.
#297 commented on
Sep 18, 2024 • 0 new comments -
docker 无法运行,报错 AssertionError: failed to initialize ttsfrd resource
#296 commented on
Sep 18, 2024 • 0 new comments -
如何微调控制停顿和数字的读法之类的?
#319 commented on
Sep 18, 2024 • 0 new comments -
About the fmax for f_bank in cosyvoice.yaml
#375 commented on
Sep 18, 2024 • 0 new comments -
推理速度很慢。
#237 commented on
Sep 19, 2024 • 0 new comments -
About the instruct fine tuning
#149 commented on
Sep 19, 2024 • 0 new comments -
请教一下当前9月更新后,优化了推理速度,使用上有什么改变么?
#359 commented on
Sep 19, 2024 • 0 new comments -
如何定制自定义音色,并将训练好的自定义音色并加入到预训练音色列表中?
#310 commented on
Sep 19, 2024 • 0 new comments -
训练能在bilibli上有个官方的指导么?避免有坑。
#135 commented on
Sep 19, 2024 • 0 new comments -
instruct模型是否支持模型微调
#230 commented on
Sep 19, 2024 • 0 new comments -
无法将克隆好的音频文件文件保存下载到本地
#392 commented on
Sep 20, 2024 • 0 new comments -
3秒极速复刻
#302 commented on
Sep 20, 2024 • 0 new comments -
NotImplementedError: Could not run 'aten::empty_strided' with arguments from the 'CUDA' backend.
#366 commented on
Sep 20, 2024 • 0 new comments