xinference 0.14.1.post1__py3-none-any.whl → 0.14.3__py3-none-any.whl

xinference/thirdparty/fish_speech/fish_speech/i18n/locale/zh_CN.json

@@ -0,0 +1,122 @@
+{
+  "16-mixed is recommended for 10+ series GPU": "10+ 系列 GPU 建议使用 16-mixed",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 到 10 秒的参考音频，适用于指定音色。",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "由 [Fish Audio](https://fish.audio) 研发的基于 VQ-GAN 和 Llama 的多语种语音合成.",
+  "Accumulate Gradient Batches": "梯度累积批次",
+  "Add to Processing Area": "加入处理区",
+  "Added path successfully!": "添加路径成功!",
+  "Advanced Config": "高级参数",
+  "Base LLAMA Model": "基础 LLAMA 模型",
+  "Batch Inference": "批量推理",
+  "Batch Size": "批次大小",
+  "Changing with the Model Path": "随模型路径变化",
+  "Chinese": "中文",
+  "Compile Model": "编译模型",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "编译模型可以显著减少推理时间，但会增加冷启动时间",
+  "Copy": "复制",
+  "Data Preprocessing": "数据预处理",
+  "Data Preprocessing Path": "数据预处理路径",
+  "Data Source": "数据源",
+  "Decoder Model Config": "解码器模型配置",
+  "Decoder Model Path": "解码器模型路径",
+  "Disabled": "禁用",
+  "Enable Reference Audio": "启用参考音频",
+  "English": "英文",
+  "Error Message": "错误信息",
+  "File Preprocessing": "文件预处理",
+  "Generate": "生成",
+  "Generated Audio": "音频",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "如果音频没有对应的文本，可以应用 ASR 辅助，支持 .txt 或 .lab 格式",
+  "Infer interface is closed": "推理界面已关闭",
+  "Inference Configuration": "推理配置",
+  "Inference Server Configuration": "推理服务器配置",
+  "Inference Server Error": "推理服务器错误",
+  "Inferring interface is launched at {}": "推理界面已在 {} 上启动",
+  "Initial Learning Rate": "初始学习率",
+  "Input Audio & Source Path for Transcription": "输入音频和转录源路径",
+  "Input Text": "输入文本",
+  "Invalid path: {}": "无效路径: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "建议使用 CUDA，如果配置较低，使用 CPU",
+  "Iterative Prompt Length, 0 means off": "迭代提示长度，0 表示关闭",
+  "Japanese": "日文",
+  "LLAMA Configuration": "LLAMA 配置",
+  "LLAMA Model Config": "LLAMA 模型配置",
+  "LLAMA Model Path": "LLAMA 模型路径",
+  "Labeling Device": "标注加速设备",
+  "LoRA Model to be merged": "要合并的 LoRA 模型",
+  "Maximum Audio Duration": "最大音频时长",
+  "Maximum Length per Sample": "每个样本的最大长度",
+  "Maximum Training Steps": "最大训练步数",
+  "Maximum tokens per batch, 0 means no limit": "每批最大令牌数，0 表示无限制",
+  "Merge": "合并",
+  "Merge LoRA": "合并 LoRA",
+  "Merge successfully": "合并成功",
+  "Minimum Audio Duration": "最小音频时长",
+  "Model Output Path": "模型输出路径",
+  "Model Size": "模型规模",
+  "Move": "移动",
+  "Move files successfully": "移动文件成功",
+  "No audio generated, please check the input text.": "没有生成音频，请检查输入文本.",
+  "No selected options": "没有选择的选项",
+  "Number of Workers": "数据加载进程数",
+  "Open Inference Server": "打开推理服务器",
+  "Open Labeler WebUI": "打开标注工具",
+  "Open Tensorboard": "打开 Tensorboard",
+  "Opened labeler in browser": "在浏览器中打开标注工具",
+  "Optional Label Language": "[可选] 标注语言",
+  "Optional online ver": "[可选] 使用在线版",
+  "Output Path": "输出路径",
+  "Path error, please check the model file exists in the corresponding path": "路径错误，请检查模型文件是否存在于相应路径",
+  "Precision": "精度",
+  "Probability of applying Speaker Condition": "应用说话人条件的概率",
+  "Put your text here.": "在此处输入文本.",
+  "Reference Audio": "参考音频",
+  "Reference Text": "参考文本",
+  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "相关代码使用 BSD-3-Clause 许可证发布，权重使用 CC BY-NC-SA 4.0 许可证发布.",
+  "Remove Selected Data": "移除选中数据",
+  "Removed path successfully!": "移除路径成功!",
+  "Repetition Penalty": "重复惩罚",
+  "Save model every n steps": "每 n 步保存模型",
+  "Select LLAMA ckpt": "选择 LLAMA 检查点",
+  "Select VITS ckpt": "选择 VITS 检查点",
+  "Select VQGAN ckpt": "选择 VQGAN 检查点",
+  "Select source file processing method": "选择源文件处理方法",
+  "Select the model to be trained (Depending on the Tab page you are on)": "根据您所在的选项卡页面选择要训练的模型",
+  "Selected: {}": "已选择: {}",
+  "Speaker": "说话人",
+  "Speaker is identified by the folder name": "自动根据父目录名称识别说话人",
+  "Start Training": "开始训练",
+  "Streaming Audio": "流式音频",
+  "Streaming Generate": "流式合成",
+  "Tensorboard Host": "Tensorboard 监听地址",
+  "Tensorboard Log Path": "Tensorboard 日志路径",
+  "Tensorboard Port": "Tensorboard 端口",
+  "Tensorboard interface is closed": "Tensorboard 界面已关闭",
+  "Tensorboard interface is launched at {}": "Tensorboard 界面已在 {} 上启动",
+  "Text is too long, please keep it under {} characters.": "文本太长，请保持在 {} 个字符以内.",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "左侧输入文件夹的路径或文件列表。无论是否选中，都将在此列表中用于后续训练.",
+  "Training Configuration": "训练配置",
+  "Training Error": "训练错误",
+  "Training stopped": "训练已停止",
+  "Type name of the speaker": "输入说话人的名称",
+  "Type the path or select from the dropdown": "输入路径或从下拉菜单中选择",
+  "Use LoRA": "使用 LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "使用 LoRA 可以节省 GPU 内存，但可能会降低模型质量",
+  "Use filelist": "使用文件列表",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "10G+ GPU 使用 large, 5G 使用 medium, 2G 使用 small",
+  "VITS Configuration": "VITS 配置",
+  "VQGAN Configuration": "VQGAN 配置",
+  "Validation Batch Size": "验证批次大小",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "查看预处理文件夹的状态 (使用滑块控制树的深度)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "我们不对模型的任何滥用负责，请在使用之前考虑您当地的法律法规.",
+  "WebUI Host": "WebUI 监听地址",
+  "WebUI Port": "WebUI 端口",
+  "Whisper Model": "Whisper 模型",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "你可以在 [这里](https://github.com/fishaudio/fish-speech) 找到源代码和 [这里](https://huggingface.co/fishaudio/fish-speech-1) 找到模型.",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "30+ 系列 GPU 建议使用 bf16-true, 10+ 系列 GPU 建议使用 16-mixed",
+  "latest": "最近的检查点",
+  "new": "创建新的检查点",
+  "Realtime Transform Text": "实时规范化文本",
+  "Normalization Result Preview (Currently Only Chinese)": "规范化结果预览",
+  "Text Normalization": "文本规范化"
+}

xinference/thirdparty/fish_speech/fish_speech/i18n/scan.py

@@ -0,0 +1,122 @@
+import ast
+import glob
+import json
+from collections import OrderedDict
+from pathlib import Path
+
+from loguru import logger
+
+from .core import DEFAULT_LANGUAGE, I18N_FILE_PATH
+
+
+def extract_i18n_strings(node):
+    i18n_strings = []
+
+    if (
+        isinstance(node, ast.Call)
+        and isinstance(node.func, ast.Name)
+        and node.func.id == "i18n"
+    ):
+        for arg in node.args:
+            if isinstance(arg, ast.Str):
+                i18n_strings.append(arg.s)
+
+    for child_node in ast.iter_child_nodes(node):
+        i18n_strings.extend(extract_i18n_strings(child_node))
+
+    return i18n_strings
+
+
+# scan the directory for all .py files (recursively)
+# for each file, parse the code into an AST
+# for each AST, extract the i18n strings
+
+strings = []
+folders = ["fish_speech", "tools"]
+# for filename in glob.iglob("**/*.py", recursive=True):
+for folder in folders:
+    for f in Path(folder).rglob("*.py"):
+        code = f.read_text(encoding="utf-8")
+        if "i18n(" in code:
+            tree = ast.parse(code)
+            i18n_strings = extract_i18n_strings(tree)
+            logger.info(f"Found {len(i18n_strings)} i18n strings in {f}")
+            strings.extend(i18n_strings)
+
+code_keys = set(strings)
+logger.info(f"Total unique: {len(code_keys)}")
+
+
+standard_file = I18N_FILE_PATH / f"{DEFAULT_LANGUAGE}.json"
+with open(standard_file, "r", encoding="utf-8") as f:
+    standard_data = json.load(f, object_pairs_hook=OrderedDict)
+standard_keys = set(standard_data.keys())
+
+# Define the standard file name
+unused_keys = standard_keys - code_keys
+logger.info(f"Found {len(unused_keys)} unused keys in {standard_file}")
+for unused_key in unused_keys:
+    logger.info(f"\t{unused_key}")
+
+missing_keys = code_keys - standard_keys
+logger.info(f"Found {len(missing_keys)} missing keys in {standard_file}")
+for missing_key in missing_keys:
+    logger.info(f"\t{missing_key}")
+
+code_keys_dict = OrderedDict()
+for s in strings:
+    code_keys_dict[s] = s
+
+# write back
+with open(standard_file, "w", encoding="utf-8") as f:
+    json.dump(code_keys_dict, f, ensure_ascii=False, indent=4, sort_keys=True)
+    f.write("\n")
+
+logger.info(f"Updated {standard_file}")
+
+
+# Define the standard file name
+standard_file = I18N_FILE_PATH / f"{DEFAULT_LANGUAGE}.json"
+
+# Find all JSON files in the directory
+dir_path = I18N_FILE_PATH
+languages = [f for f in dir_path.glob("*.json") if f.stem != DEFAULT_LANGUAGE]
+
+# Load the standard file
+with open(standard_file, "r", encoding="utf-8") as f:
+    standard_data = json.load(f, object_pairs_hook=OrderedDict)
+
+# Loop through each language file
+for lang_file in languages:
+    # Load the language file
+    with open(lang_file, "r", encoding="utf-8") as f:
+        lang_data = json.load(f, object_pairs_hook=OrderedDict)
+
+    # Find the difference between the language file and the standard file
+    diff = set(standard_data.keys()) - set(lang_data.keys())
+
+    miss = set(lang_data.keys()) - set(standard_data.keys())
+
+    # Add any missing keys to the language file
+    for key in diff:
+        lang_data[key] = "#!" + key
+        logger.info(f"Added missing key: {key} to {lang_file}")
+
+    # Del any extra keys to the language file
+    for key in miss:
+        del lang_data[key]
+        logger.info(f"Del extra key: {key} from {lang_file}")
+
+    # Sort the keys of the language file to match the order of the standard file
+    lang_data = OrderedDict(
+        sorted(lang_data.items(), key=lambda x: list(standard_data.keys()).index(x[0]))
+    )
+
+    # Save the updated language file
+    with open(lang_file, "w", encoding="utf-8") as f:
+        json.dump(lang_data, f, ensure_ascii=False, indent=4, sort_keys=True)
+        f.write("\n")
+
+    logger.info(f"Updated {lang_file}")
+
+logger.info("Done")

xinference/thirdparty/fish_speech/fish_speech/models/text2semantic/lit_module.py

@@ -0,0 +1,202 @@
+from typing import Any, Optional
+
+import lightning as L
+import torch
+import torch.nn.functional as F
+from lightning.pytorch.utilities.types import OptimizerLRScheduler
+
+import fish_speech.utils as utils
+from fish_speech.conversation import CODEBOOK_PAD_TOKEN_ID
+from fish_speech.models.text2semantic.llama import NaiveTransformer
+
+log = utils.RankedLogger(__name__, rank_zero_only=True)
+
+
+class TextToSemantic(L.LightningModule):
+    def __init__(
+        self,
+        model: NaiveTransformer,
+        optimizer: Any,
+        lr_scheduler: Any,
+    ):
+        super().__init__()
+
+        self.model = model
+        self.optimizer_builder = optimizer
+        self.lr_scheduler_builder = lr_scheduler
+
+    def forward(self, x):
+        return self.model(x)
+
+    def on_save_checkpoint(self, checkpoint):
+        # Save only LoRA parameters
+        state_dict = checkpoint["state_dict"]
+        use_lora = any("lora" in name for name in state_dict.keys())
+        if not use_lora:
+            return
+
+        for name in list(state_dict.keys()):
+            if "lora" not in name:
+                state_dict.pop(name)
+
+    def configure_optimizers(self) -> OptimizerLRScheduler:
+        # Get weight decay parameters
+        weight_decay_parameters, other_parameters = [], []
+        for name, param in self.named_parameters():
+            if ".bias" in name or "norm.weight" in name or ".embeddings." in name:
+                other_parameters.append(param)
+            else:
+                weight_decay_parameters.append(param)
+
+        optimizer = self.optimizer_builder(
+            [
+                {"params": weight_decay_parameters},
+                {"params": other_parameters, "weight_decay": 0.0},
+            ]
+        )
+
+        # Print the parameters and their weight decay
+        for i in optimizer.param_groups:
+            log.info(
+                f"Set weight decay: {i['weight_decay']} for {len(i['params'])} parameters"
+            )
+
+        lr_scheduler = self.lr_scheduler_builder(optimizer)
+
+        return {
+            "optimizer": optimizer,
+            "lr_scheduler": {
+                "scheduler": lr_scheduler,
+                "interval": "step",
+            },
+        }
+
+    # Copied from https://github.com/eric-mitchell/direct-preference-optimization/blob/main/trainers.py#L90
+    def get_batch_logps(
+        self,
+        logits: torch.FloatTensor,
+        labels: torch.LongTensor,
+        average_log_prob: bool = False,
+    ) -> torch.FloatTensor:
+        """Compute the log probabilities of the given labels under the given logits.
+
+        Args:
+            logits: Logits of the model (unnormalized). Shape: (batch_size, sequence_length, codebook_size, vocab_size)
+            labels: Labels for which to compute the log probabilities. Label tokens with a value of -100 are ignored. Shape: (batch_size, sequence_length, codebook_size)
+            average_log_prob: If True, return the average log probability per (non-masked) token. Otherwise, return the sum of the log probabilities of the (non-masked) tokens.
+
+        Returns:
+            A tensor of shape (batch_size,) containing the average/sum log probabilities of the given labels under the given logits.
+        """
+        assert logits.shape[:-1] == labels.shape
+
+        labels = labels.clone()
+        loss_mask = labels != -100
+
+        # dummy token; we'll ignore the losses on these tokens later
+        labels[labels == -100] = 0
+
+        per_token_logps = torch.gather(
+            logits.log_softmax(-1), dim=-1, index=labels.unsqueeze(-1)
+        ).squeeze(-1)
+
+        if average_log_prob:
+            return (per_token_logps * loss_mask).sum(-1) / loss_mask.sum(-1)
+        else:
+            return (per_token_logps * loss_mask).sum(-1)
+
+    def _step(self, batch, batch_idx, stage: str):
+        is_train = stage == "train"
+
+        if is_train:
+            # Key part to make lora work
+            # Otherwise the parameters are merged, which lead to incorrect gradients
+            self.model.train()
+
+        # Do positive and negative samples in the same batch to speed up training
+        labels = batch["labels"]
+        outputs = self.model(
+            inp=batch["inputs"],
+            key_padding_mask=batch["attention_masks"],
+        )
+        token_logits = outputs.token_logits
+        codebook_logits = outputs.codebook_logits
+
+        # Generate labels
+        base_loss = F.cross_entropy(
+            token_logits.view(-1, token_logits.size(-1)),
+            labels[:, 0].reshape(-1),
+            ignore_index=-100,
+        )
+
+        codebook_labels = labels[:, 1 : 1 + self.model.config.num_codebooks].mT
+        semantic_loss = F.cross_entropy(
+            codebook_logits.view(-1, codebook_logits.size(-1)),
+            codebook_labels.reshape(-1),
+            ignore_index=-100,
+        )
+
+        loss = base_loss + semantic_loss
+
+        self.log(
+            f"{stage}/loss",
+            loss,
+            on_step=is_train,
+            on_epoch=not is_train,
+            prog_bar=True,
+            logger=True,
+            sync_dist=not is_train,
+        )
+
+        self.log(
+            f"{stage}/base_loss",
+            base_loss,
+            on_step=is_train,
+            on_epoch=not is_train,
+            prog_bar=False,
+            logger=True,
+            sync_dist=not is_train,
+        )
+
+        self.log(
+            f"{stage}/semantic_loss",
+            semantic_loss,
+            on_step=is_train,
+            on_epoch=not is_train,
+            prog_bar=False,
+            logger=True,
+            sync_dist=not is_train,
+        )
+
+        # Top-5 accuracy
+        accuracy = self.get_accuracy(codebook_logits, codebook_labels)
+        self.log(
+            f"{stage}/top_5_accuracy",
+            accuracy,
+            on_step=is_train,
+            on_epoch=not is_train,
+            prog_bar=True,
+            logger=True,
+            sync_dist=not is_train,
+        )
+
+        return loss
+
+    def get_accuracy(self, logits, labels):
+        mask = (labels != -100) & (labels != CODEBOOK_PAD_TOKEN_ID)
+        if mask.sum() == 0:
+            return torch.tensor(0.0, device=logits.device)
+
+        _, indices = logits.topk(5, dim=-1)
+        correct = indices.eq(labels.unsqueeze(-1))
+        correct[~mask] = 0
+        correct = correct.sum()
+        accuracy = correct / mask.sum()
+
+        return accuracy
+
+    def training_step(self, batch, batch_idx):
+        return self._step(batch, batch_idx, "train")
+
+    def validation_step(self, batch, batch_idx):
+        return self._step(batch, batch_idx, "val")