Method __init__

src/voxcpm/core.py:15–101

Initialize VoxCPM TTS pipeline. Args: voxcpm_model_path: Local filesystem path to the VoxCPM model assets (weights, configs, etc.). Typically the directory returned by a prior download step. zipenhancer_model_path: ModelScope acoustic

(
        self,
        voxcpm_model_path: str,
        zipenhancer_model_path: str | None = "iic/speech_zipenhancer_ans_multiloss_16k_base",
        enable_denoiser: bool = True,
        optimize: bool = True,
        device: str | None = None,
        lora_config: Optional[LoRAConfig] = None,
        lora_weights_path: Optional[str] = None,
    )

class VoxCPM:
    def __init__(
        self,
        voxcpm_model_path: str,
        zipenhancer_model_path: str | None = "iic/speech_zipenhancer_ans_multiloss_16k_base",
        enable_denoiser: bool = True,
        optimize: bool = True,
        device: str | None = None,
        lora_config: Optional[LoRAConfig] = None,
        lora_weights_path: Optional[str] = None,
    ):
        """Initialize VoxCPM TTS pipeline.

        Args:
            voxcpm_model_path: Local filesystem path to the VoxCPM model assets
                (weights, configs, etc.). Typically the directory returned by
                a prior download step.
            zipenhancer_model_path: ModelScope acoustic noise suppression model
                id or local path. If None, denoiser will not be initialized.
            enable_denoiser: Whether to initialize the denoiser pipeline.
            optimize: Whether to optimize the model with torch.compile. True by default, but can be disabled for debugging.
            device: Runtime device. If set to ``None`` or ``"auto"``, VoxCPM
                will choose automatically (preferring CUDA, then MPS, then CPU).
                If set explicitly, that device is used or a clear error is raised.
            lora_config: LoRA configuration for fine-tuning. If lora_weights_path is
                provided without lora_config, a default config will be created.
            lora_weights_path: Path to pre-trained LoRA weights (.pth file or directory
                containing lora_weights.ckpt). If provided, LoRA weights will be loaded.
        """
        print(
            f"voxcpm_model_path: {voxcpm_model_path}, zipenhancer_model_path: {zipenhancer_model_path}, enable_denoiser: {enable_denoiser}",
            file=sys.stderr,
        )

        # If lora_weights_path is provided but no lora_config, create a default one
        if lora_weights_path is not None and lora_config is None:
            lora_config = LoRAConfig(
                enable_lm=True,
                enable_dit=True,
                enable_proj=False,
            )
            print(f"Auto-created default LoRAConfig for loading weights from: {lora_weights_path}", file=sys.stderr)

        # Determine model type from config.json architecture field
        config_path = os.path.join(voxcpm_model_path, "config.json")
        with open(config_path, "r", encoding="utf-8") as f:
            config = json.load(f)
        arch = config.get("architecture", "voxcpm").lower()

        if arch == "voxcpm2":
            self.tts_model = VoxCPM2Model.from_local(
                voxcpm_model_path,
                optimize=optimize,
                device=device,
                lora_config=lora_config,
            )
            print("Loaded VoxCPM2Model", file=sys.stderr)
        elif arch == "voxcpm":
            self.tts_model = VoxCPMModel.from_local(