modelscope / KAN-TTS

KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech

modelscope/KAN-TTS Issues

官方能提供转模型转onnx的脚本吗？自己做有点困难
Updated 14 days ago9
纯英文效果不好，怎么破？一个单词一个单词往外蹦。。
Updated a month ago3
windows目前不支持部署，如果想尝试的大家散了吧
Closed a month ago
Sambert微调声学模型失败RuntimeError: Error(s) in loading state_dict for KanTtsSAMBERT: size mismatch for spk_tokenizer.weight: copying a param with shape torch.Size([9, 32]) from checkpoint, the shape in current model is torch.Size([10, 32]).
Closed 9 months ago2
Infering is so slow.
Updated 2 months ago2
体验api不支持调整语速音量吗？
Closed 2 months ago1
Need python 3.9 & python 3.10 supports
Updated 3 months ago2
如何区别多音字
Updated 3 months ago
上周下的ttsfrd0.2.6版本现在没了？
Closed 3 months ago
合成中文儿化音怎么处理？
Updated 3 months ago
min_wav_length 去除0.5s以下的样本
Updated 4 months ago2
英文字母A的发音有问题
Updated 4 months ago
how to deploy the model via c++
Updated 5 months ago5
请教一下，语音合成，语义相关问题
Updated 5 months ago1
请问ttsfrd有计划发布windows的版本吗？
Updated 6 months ago
[CONTRIBUTION] Speech Dataset Generator
Updated 6 months ago
训练报错，拉取SambertHifigan语音合成-多语言-多人预训练-16k多语言模型后，用kantts的sambert这部分训练会报错
Closed 6 months ago1
希望像 FunASR 一样，提供 C++ 推理
Updated 7 months ago4
关于多说话人的疑问
Updated 7 months ago
SAM-BERT流式
Updated 8 months ago1
训练步数越多反而效果不好有杂音
Updated 9 months ago1
运行过程中，不断打印“Load pinyin_en_mix_dict failed”
Updated 9 months ago7
带情感的语音合成
Closed 9 months ago
How to adjust speech rate with ssml format
Updated 10 months ago
Is there any open source tools to generate intervals in mit format?
Closed a year ago
训练到一半出现的报错 RuntimeError: torch.cat(): expected a non-empty list of Tensors
Updated a year ago
auto_label 出错 Authentication token does not exist, failed to access model
Closed a year ago
效果很好，但是断句延迟时间太长，看起来不连贯。是否有方法解决？
Closed a year ago1
训练声码器的时候报错 CUFFT_INTERNAL_ERROR
Updated a year ago
KeyError: 'test_male'
Updated a year ago2
在声音特征提取的步骤中出错
Updated a year ago
关于ttsfrd
Updated a year ago
hifigan结构设计？
Updated a year ago1
subprocess.CalledProcessError: Command '['git', 'rev-parse', 'HEAD']' returned non-zero exit status 128.
Updated a year ago2
About license
Updated a year ago1
Could not load library libcudnn_cnn_infer.so.8.
Updated a year ago
SyntaxError: invalid syntax (3690364265.py, line 2) in notebook
Updated a year ago
train_sambert报错
Updated a year ago
What do the categories in fp_category_list = ["FP", "I", "N", "Q"] mean?
Updated a year ago1
kantts/bin/text_to_wav.py 加载SambertHifigan语音合成-中文-多人预训练-16k 合成音频报错
Closed a year ago1
音频格式转换时出错，TypeError: check_argument_types() missing 1 required positional argument: 'func'
Updated a year ago1
有多说话人TTS从头训练的教程吗，看到的都是单个说话人的
Updated a year ago
为什么不支持python3.10
Updated a year ago
请教推理的时候出现Load pinyin_en_mix_dict failed如何避免？
Closed a year ago1
pqmf
Updated a year ago
ttsfrd 支持自定义字典吗？
Updated a year ago
sambert和hifigan的微调命名规则不统一，推理男声必须说话人为F7
Updated a year ago
run WuuShanghai and Cantonese error in KAN-TTS or ModelScope
Updated a year ago
Gained a bug when modifying the speech rate （inference stage）
Closed a year ago2
运行text_to_wav.py时一个小bug
Updated a year ago