{ "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.": "### Model comparison\n> You can get model ID (long) from `View model information` below.\n\nCalculate a similarity between two models.", "### Model extraction\n> Enter the path of the large file model under the 'logs' folder.\n\nThis is useful if you want to stop training halfway and manually extract and save a small model file, or if you want to test an intermediate model.": "### 模型提取\n> 输入logs文件夹下大文件模型路径\n\n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 fusion\nCan be used to test timbre fusion.": "### Model fusion\nCan be used to test timbre fusion.", "### Modify model information\n> Only supported for small model files extracted from the 'weights' folder.": "### 修改模型信息\n> 仅支持weights文件夹下提取的小模型文件", "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.": "### Step 1. Fill in the experimental configuration.\nExperimental data is stored in the 'logs' folder, with each experiment having a separate folder. Manually enter the experiment name path, which contains the experimental configuration, logs, and trained model files.", "### Step 2. Audio processing. \n#### 1. Slicing.\nAutomatically traverse all files in the training folder that can be decoded into audio and perform slice normalization. Generates 2 wav folders in the experiment directory. Currently, only single-singer/speaker training is supported.": "### 第二步 音频处理\n#### 1. 音频切片\n自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练.", "### Step 3. Start training.\nFill in the training settings and start training the model and index.": "### 第三步 开始训练\n填写训练设置, 开始训练模型和索引.", "### View model information\n> Only supported for small model files extracted from the 'weights' folder.": "### 查看模型信息\n> 仅支持weights文件夹下提取的小模型文件", "#### 2. Feature extraction.\nUse CPU to extract pitch (if the model has pitch), use GPU to extract features (select GPU index).": "#### 2. 特征提取\n使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号).", "Actually calculated": "实际计算", "Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume": "輸入源音量包絡替換輸出音量包絡融合比例，越靠近1越使用輸出包絡", "Algorithmic delays (ms)": "算法延遲(ms)", "All processes have been completed!": "全流程结束！", "Audio device": "音訊設備", "Auto-detect index path and select from the dropdown": "自動檢測index路徑,下拉式選擇(dropdown)", "Batch conversion. Enter the folder containing the audio files to be converted or upload multiple audio files. The converted audio will be output in the specified folder (default: 'opt').": "批量轉換，輸入待轉換音頻資料夾，或上傳多個音頻檔案，在指定資料夾(默認opt)下輸出轉換的音頻。", "Batch inference": "批量推理", "Batch processing for vocal accompaniment separation using the UVR5 model.
Example of a valid folder path format: D:\\path\\to\\input\\folder (copy it from the file manager address bar).
The model is divided into three categories:
1. Preserve vocals: Choose this option for audio without harmonies. It preserves vocals better than HP5. It includes two built-in models: HP2 and HP3. HP3 may slightly leak accompaniment but preserves vocals slightly better than HP2.
2. Preserve main vocals only: Choose this option for audio with harmonies. It may weaken the main vocals. It includes one built-in model: HP5.
3. De-reverb and de-delay models (by FoxJoy):
  (1) MDX-Net: The best choice for stereo reverb removal but cannot remove mono reverb;
 (234) DeEcho: Removes delay effects. Aggressive mode removes more thoroughly than Normal mode. DeReverb additionally removes reverb and can remove mono reverb, but not very effectively for heavily reverberated high-frequency content.
De-reverb/de-delay notes:
1. The processing time for the DeEcho-DeReverb model is approximately twice as long as the other two DeEcho models.
2. The MDX-Net-Dereverb model is quite slow.
3. The recommended cleanest configuration is to apply MDX-Net first and then DeEcho-Aggressive.": "使用UVR5模型進行人聲伴奏分離的批次處理。
有效資料夾路徑格式的例子：D:\\path\\to\\input\\folder（從檔案管理員地址欄複製）。
模型分為三類：
1. 保留人聲：選擇這個選項適用於沒有和聲的音訊。它比HP5更好地保留了人聲。它包括兩個內建模型：HP2和HP3。HP3可能輕微漏出伴奏，但比HP2更好地保留了人聲；
2. 僅保留主人聲：選擇這個選項適用於有和聲的音訊。它可能會削弱主人聲。它包括一個內建模型：HP5。
3. 消除混響和延遲模型（由FoxJoy提供）：
  (1) MDX-Net：對於立體聲混響的移除是最好的選擇，但不能移除單聲道混響；
 (234) DeEcho：移除延遲效果。Aggressive模式比Normal模式移除得更徹底。DeReverb另外移除混響，可以移除單聲道混響，但對於高頻重的板式混響移除不乾淨。
消除混響/延遲注意事項：
1. DeEcho-DeReverb模型的處理時間是其他兩個DeEcho模型的近兩倍；
2. MDX-Net-Dereverb模型相當慢；
3. 個人推薦的最乾淨配置是先使用MDX-Net，然後使用DeEcho-Aggressive。", "Batch size per GPU": "每张显卡的batch_size", "Cache all training sets to GPU memory. Caching small datasets (less than 10 minutes) can speed up training, but caching large datasets will consume a lot of GPU memory and may not provide much speed improvement": "是否緩存所有訓練集至 VRAM。小於10分鐘的小數據可緩存以加速訓練，大數據緩存會爆 VRAM 也加不了多少速度", "Calculate": "计算", "Choose sample rate of the device": "使用设备采样率", "Choose sample rate of the model": "使用模型采样率", "Convert": "轉換", "Device type": "设备类型", "Enable phase vocoder": "启用相位声码器", "Enter the GPU index(es) separated by '-', e.g., 0-0-1 to use 2 processes in GPU0 and 1 process in GPU1": "rmvpe卡號配置：以-分隔輸入使用的不同進程卡號,例如0-0-1使用在卡0上跑2個進程並在卡1上跑1個進程", "Enter the GPU index(es) separated by '-', e.g., 0-1-2 to use GPU 0, 1, and 2": "以-分隔輸入使用的卡號, 例如 0-1-2 使用卡0和卡1和卡2", "Enter the experiment name": "輸入實驗名稱", "Enter the path of the audio folder to be processed": "輸入待處理音頻資料夾路徑", "Enter the path of the audio folder to be processed (copy it from the address bar of the file manager)": "輸入待處理音頻資料夾路徑(去檔案管理器地址欄拷貝即可)", "Enter the path of the training folder": "輸入訓練檔案夾路徑", "Exist": "有", "Export Onnx": "Onnx导出", "Export Onnx Model": "导出Onnx模型", "Export audio (click on the three dots in the lower right corner to download)": "輸出音頻(右下角三個點，點了可以下載)", "Export file format": "導出檔格式", "Extra inference time": "額外推理時長", "Extract": "提取", "F0 curve file (optional). One pitch per line. Replaces the default F0 and pitch modulation": "F0曲線檔案，可選，一行一個音高，代替預設的F0及升降調", "FAQ (Frequently Asked Questions)": "常見問題解答", "Fade length": "淡入淡出長度", "Fail": "失败", "Feature extraction": "特徵提取", "Feature searching ratio": "檢索特徵佔比", "Formant offset": "共振偏移", "Fusion": "融合", "GPU Information": "顯示卡資訊", "General settings": "一般設定", "Hidden": "不显示", "ID of model A (long)": "A模型ID(长)", "ID of model B (long)": "B模型ID(长)", "ID(long)": "ID(long)", "ID(short)": "ID(短)", "If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.": ">=3則使用對harvest音高識別的結果使用中值濾波，數值為濾波半徑，使用可以削弱啞音", "Inference time (ms)": "推理時間(ms)", "Inferencing voice": "推理音色", "Information": "信息", "Input device": "輸入設備", "Input noise reduction": "輸入降噪", "Input voice monitor": "输入监听", "Link index to outside folder": "链接索引到外部", "Load model": "載入模型", "Load pre-trained base model D path": "加載預訓練底模D路徑", "Load pre-trained base model G path": "加載預訓練底模G路徑", "Loudness factor": "響度因子", "Model": "模型", "Model Author": "模型作者", "Model Author (Nullable)": "模型作者(可空)", "Model Inference": "模型推理", "Model architecture version": "模型版本型號", "Model info": "模型信息", "Model information to be modified": "要改的模型資訊", "Model information to be placed": "要置入的模型資訊", "Model name": "模型名", "Modify": "修改", "Multiple audio files can also be imported. If a folder path exists, this input is ignored.": "也可批量输入音频文件, 二选一, 优先读文件夹", "No": "否", "None": "None", "Not exist": "无", "Number of CPU processes used for harvest pitch algorithm": "harvest進程數", "Number of CPU processes used for pitch extraction and data processing": "提取音高和處理數據使用的CPU進程數", "One-click training": "一鍵訓練", "Onnx Export Path": "Onnx输出路径", "Output converted voice": "输出变声", "Output device": "輸出設備", "Output information": "輸出訊息", "Output noise reduction": "輸出降噪", "Path to Model": "模型路徑", "Path to Model A": "A模型路徑", "Path to Model B": "B模型路徑", "Path to the feature index file. Leave blank to use the selected result from the dropdown": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果", "Performance settings": "效能設定", "Pitch detection algorithm": "音高演算法", "Pitch guidance (f0)": "音高引导(f0)", "Pitch settings": "音調設定", "Please choose the .index file": "请选择index文件", "Please choose the .pth file": "请选择pth文件", "Please specify the speaker/singer ID": "請指定說話人id", "Process data": "處理資料", "Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but it may reduce indexing accuracy": "保護清輔音和呼吸聲，防止電音撕裂等artifact，拉滿0.5不開啟，調低加大保護力度但可能降低索引效果", "RVC Model Path": "RVC模型路径", "Read from model": "从模型中读取", "Refresh voice list and index path": "刷新音色列表和索引路徑", "Reload device list": "重載設備列表", "Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling": "後處理重採樣至最終採樣率，0為不進行重採樣", "Response threshold": "響應閾值", "Sample length": "取樣長度", "Sampling rate": "采样率", "Save a small final model to the 'weights' folder at each save point": "是否在每次保存時間點將最終小模型保存至weights檔夾", "Save file name (default: same as the source file)": "儲存的檔案名，預設空為與來源檔案同名", "Save frequency (save_every_epoch)": "保存頻率save_every_epoch", "Save name": "儲存名", "Save only the latest '.ckpt' file to save disk space": "是否僅保存最新的ckpt檔案以節省硬碟空間", "Saved model name (without extension)": "儲存的模型名不帶副檔名", "Sealing date": "封装时间", "Select Speaker/Singer ID": "請選擇說話人ID", "Select the .index file": "選擇 .index 檔案", "Select the .pth file": "選擇 .pth 檔案", "Select the pitch extraction algorithm ('pm': faster extraction but lower-quality speech; 'harvest': better bass but extremely slow; 'crepe': better quality but GPU intensive), 'rmvpe': best quality, and little GPU requirement": "選擇音高提取演算法,輸入歌聲可用pm提速,harvest低音好但巨慢無比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU", "Select the pitch extraction algorithm: when extracting singing, you can use 'pm' to speed up. For high-quality speech with fast performance, but worse CPU usage, you can use 'dio'. 'harvest' results in better quality but is slower. 'rmvpe' has the best results and consumes less CPU/GPU": "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,rmvpe效果最好且微吃CPU/GPU", "Similarity": "相似度", "Similarity (from 0 to 1)": "相似度(0到1)", "Single inference": "单次推理", "Specify output folder": "指定輸出資料夾", "Specify the output folder for accompaniment": "指定输出非主人声文件夹", "Specify the output folder for vocals": "指定输出主人声文件夹", "Start audio conversion": "開始音訊轉換", "Step 1: Processing data": "step1:正在处理数据", "Step 3a: Model training started": "step3a:正在训练模型", "Stop audio conversion": "停止音訊轉換", "Successfully built index into": "成功构建索引到", "Takeover WASAPI device": "独占 WASAPI 设备", "Target sample rate": "目標取樣率", "The audio file to be processed": "待处理音频文件", "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible.
If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory Agreement-LICENSE.txt for details.": "本軟體以MIT協議開源，作者不對軟體具備任何控制力，使用軟體者、傳播軟體導出的聲音者自負全責。
如不認可該條款，則不能使用或引用軟體包內任何程式碼和檔案。詳見根目錄使用需遵守的協議-LICENSE.txt。", "Total training epochs (total_epoch)": "總訓練輪數total_epoch", "Train": "訓練", "Train feature index": "訓練特徵索引", "Train model": "訓練模型", "Training complete. You can check the training logs in the console or the 'train.log' file under the experiment folder.": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log", "Transpose (integer, number of semitones, raise by an octave: 12, lower by an octave: -12)": "變調(整數、半音數量、升八度12降八度-12)", "Unfortunately, there is no compatible GPU available to support your training.": "很遗憾您这没有能用的显卡来支持您训练", "Unknown": "Unknown", "Unload model to save GPU memory": "卸載音色節省 VRAM", "Version": "版本", "View": "查看", "Vocals/Accompaniment Separation & Reverberation Removal": "伴奏人聲分離&去混響&去回聲", "Weight (w) for Model A": "A模型權重", "Whether the model has pitch guidance": "模型是否帶音高指導", "Whether the model has pitch guidance (1: yes, 0: no)": "模型是否帶音高指導，1是0否", "Whether the model has pitch guidance (required for singing, optional for speech)": "模型是否帶音高指導（唱歌一定要，語音可以不要）", "Yes": "是", "ckpt Processing": "ckpt處理", "index path cannot contain unicode characters": "index文件路径不可包含中文", "pth path cannot contain unicode characters": "pth文件路径不可包含中文", "step2:Pitch extraction & feature extraction": "step2:正在提取音高&正在提取特征" }