71 lines
6.1 KiB
JSON
71 lines
6.1 KiB
JSON
{
|
||
"模型推理": "Model inference",
|
||
"推理音色": "Inferencing timbre",
|
||
"刷新音色列表": "Refresh timbre list",
|
||
"卸载音色省显存": "Unload timbre to save GPU memory",
|
||
"请选择说话人id": "Please select a speaker id",
|
||
"变调（整数，半音数量，升八度12降八度-12）": "Pitch shift (integer, number of semitones, up to 12 octaves or down to -12 octaves)",
|
||
"输入待处理音频文件路径(默认是正确格式示例": "Input the path of the audio file to be processed (the default format is an example of the correct format)",
|
||
"选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比": "Select the algorithm for pitch extraction. Use 'pm' to speed up for singing voices, or use 'harvest' for better low-pitched voices, but it is extremely slow.",
|
||
"特征检索库文件路径": "Feature search database file path",
|
||
"特征文件路径": "Feature file path",
|
||
"F0曲线文件，可选，一行一个音高，代替默认F0及升降调": "F0 curve file, optional. One pitch per line to replace default F0 and pitch shifting.",
|
||
"转换": "Conversion",
|
||
"输出信息": "Output information",
|
||
"输出音频(右下角三个点,点了可以下载": "Output audio (three dots in the lower right corner, click to download)",
|
||
"指定输出文件夹": "Specify output folder",
|
||
"检索特征占比": "Search feature ratio",
|
||
"输入待处理音频文件夹路径(去文件管理器地址栏拷就行了": "Input the path of the audio file folder to be processed (just copy it from the address bar of the file manager)",
|
||
"也可批量输入音频文件，二选一，优先读文件夹": "Batch input of audio files is also available. Choose one of them, and the folder has a higher priority.",
|
||
"伴奏人声分离": "Accompaniment and vocal separation",
|
||
"输入待处理音频文件夹路径": "Input audio folder path",
|
||
"模型": "Model",
|
||
"指定输出人声文件夹": "Specify output vocal folder",
|
||
"指定输出乐器文件夹": "Specify output instrumental folder",
|
||
"训练": "Train",
|
||
"输入实验名": "Input experiment name",
|
||
"目标采样率": "Target sample rate",
|
||
"模型是否带音高指导(唱歌一定要，语音可以不要": "Does the model have pitch guidance? (Necessary for singing, not necessary for speech)",
|
||
"输入训练文件夹路径": "Input training folder path",
|
||
"请指定说话人id": "Please specify speaker ID",
|
||
"处理数据": "Process data",
|
||
"以-分隔输入使用的卡号，例如 0-1-2 使用卡0和卡1和卡2": "Input card numbers to use, separated by '-'. For example, '0-1-2' means using card 0, card 1, and card 2.",
|
||
"显卡信息": "GPU information",
|
||
"提取音高使用的CPU进程数": "Number of CPU processes used for pitch extraction",
|
||
"选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "Select pitch extraction algorithm: Use 'pm' for faster processing of singing voice, 'dio' for high-quality speech but slower processing, and 'harvest' for the best quality but slowest processing.",
|
||
"特征提取": "Feature extraction",
|
||
"保存频率save_every_epoch": "Save frequency (save_every_epoch)",
|
||
"总训练轮数total_epoch": "Total training epochs (total_epoch)",
|
||
"是否仅保存最新的ckpt文件以节省硬盘空间": "Whether to save only the latest ckpt file to save disk space",
|
||
"是否缓存所有训练集至显存。10min以下小数据可缓存以加速训练，大数据缓存会炸显存也加不了多少速": "Whether to cache all training sets in the video memory. Small data less than 10 minutes can be cached to speed up training, but caching large data will cause the video memory to explode and not add much speed.",
|
||
"加载预训练底模G路径": "Load pre-trained base model G path.",
|
||
"加载预训练底模D路径": "Load pre-trained base model D path.",
|
||
"训练模型": "Train model.",
|
||
"训练特征索引": "Train feature index.",
|
||
"一键训练": "One-click training.",
|
||
"ckpt处理": "ckpt processing.",
|
||
"A模型路径": "A model path.",
|
||
"B模型路径": "B model path.",
|
||
"A模型权重": "A model weight.",
|
||
"模型是否带音高指导": "Whether the model has pitch guidance.",
|
||
"要置入的模型信息": "Model information to be placed.",
|
||
"保存的模型名不带后缀": "Saved model name without extension.",
|
||
"融合": "Fusion.",
|
||
"修改模型信息(仅支持weights文件夹下提取的小模型文件": "Modify model information (only supports small model files extracted under the weights folder)",
|
||
"模型路径": "Model path",
|
||
"要改的模型信息": "Model information to be modified",
|
||
"保存的文件名，默认空为和源文件同名": "Saved file name, empty by default to use the same name as the source file",
|
||
"修改": "Modify",
|
||
"查看模型信息(仅支持weights文件夹下提取的小模型文件": "View model information (only supports small model files extracted under the weights folder)",
|
||
"查看": "View",
|
||
"模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "Model extraction (input the path of the large file model under the logs folder), suitable for situations where you do not want to continue training halfway and the model has not automatically extracted and saved a small file model, or when you want to test intermediate models",
|
||
"保存名": "Save Name",
|
||
"模型是否带音高指导,1是0否": "Whether the model comes with pitch guidance, 1 for yes, 0 for no",
|
||
"提取": "Extract",
|
||
"招募音高曲线前端编辑器": "Recruit front-end editors for pitch curves",
|
||
"点击查看交流、问题反馈群号": "Click to view the communication and problem feedback group number",
|
||
"输入设备/Input Device": "Input device",
|
||
"输出设备/Output Device": "Output device",
|
||
"音频设备(请使用同种类驱动)/Audio Devices": "Audio devices (please use the same type of driver)",
|
||
"音调设置/Pitch Offset": "Pitch setting / Pitch Offset"
|
||
} |