Delete configs

configs/32k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 50,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.99975,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 100,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 32000,
-    "filter_length": 1024,
-    "hop_length": 320,
-    "win_length": 1024,
-    "n_mel_channels": 80,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,8,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [20,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/40k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 50,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.99975,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 100,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 40000,
-    "filter_length": 2048,
-    "hop_length": 400,
-    "win_length": 2048,
-    "n_mel_channels": 125,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/48k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 50,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.99975,
-    "segment_size": 17280,
-    "init_lr_ratio": 2,
-    "warmup_epochs": 100,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 48000,
-    "filter_length": 2048,
-    "hop_length": 480,
-    "win_length": 2048,
-    "n_mel_channels": 128,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [12,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [24,20,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/config.json

@@ -1 +0,0 @@
-{"pth_path": "assets/weights/kikiV1.pth", "index_path": "logs/kikiV1.index", "sg_input_device": "VoiceMeeter Output (VB-Audio Vo (MME)", "sg_output_device": "VoiceMeeter Input (VB-Audio Voi (MME)", "threhold": -45.0, "pitch": 2.0, "rms_mix_rate": 0.0, "index_rate": 0.0, "block_time": 0.52, "crossfade_length": 0.15, "extra_time": 2.46, "n_cpu": 6.0, "use_jit": false, "f0method": "rmvpe"}

configs/config.py

@@ -1,251 +0,0 @@
-import argparse
-import os
-import sys
-import json
-from multiprocessing import cpu_count
-
-import torch
-
-try:
-    import intel_extension_for_pytorch as ipex  # pylint: disable=import-error, unused-import
-
-    if torch.xpu.is_available():
-        from infer.modules.ipex import ipex_init
-
-        ipex_init()
-except Exception:  # pylint: disable=broad-exception-caught
-    pass
-import logging
-
-logger = logging.getLogger(__name__)
-
-
-version_config_list = [
-    "v1/32k.json",
-    "v1/40k.json",
-    "v1/48k.json",
-    "v2/48k.json",
-    "v2/32k.json",
-]
-
-
-def singleton_variable(func):
-    def wrapper(*args, **kwargs):
-        if not wrapper.instance:
-            wrapper.instance = func(*args, **kwargs)
-        return wrapper.instance
-
-    wrapper.instance = None
-    return wrapper
-
-
-@singleton_variable
-class Config:
-    def __init__(self):
-        self.device = "cuda:0"
-        self.is_half = True
-        self.use_jit = False
-        self.n_cpu = 0
-        self.gpu_name = None
-        self.json_config = self.load_config_json()
-        self.gpu_mem = None
-        (
-            self.python_cmd,
-            self.listen_port,
-            self.iscolab,
-            self.noparallel,
-            self.noautoopen,
-            self.dml,
-        ) = self.arg_parse()
-        self.instead = ""
-        self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
-
-    @staticmethod
-    def load_config_json() -> dict:
-        d = {}
-        for config_file in version_config_list:
-            with open(f"configs/{config_file}", "r") as f:
-                d[config_file] = json.load(f)
-        return d
-
-    @staticmethod
-    def arg_parse() -> tuple:
-        exe = sys.executable or "python"
-        parser = argparse.ArgumentParser()
-        parser.add_argument("--port", type=int, default=7865, help="Listen port")
-        parser.add_argument("--pycmd", type=str, default=exe, help="Python command")
-        parser.add_argument("--colab", action="store_true", help="Launch in colab")
-        parser.add_argument(
-            "--noparallel", action="store_true", help="Disable parallel processing"
-        )
-        parser.add_argument(
-            "--noautoopen",
-            action="store_true",
-            help="Do not open in browser automatically",
-        )
-        parser.add_argument(
-            "--dml",
-            action="store_true",
-            help="torch_dml",
-        )
-        cmd_opts = parser.parse_args()
-
-        cmd_opts.port = cmd_opts.port if 0 <= cmd_opts.port <= 65535 else 7865
-
-        return (
-            cmd_opts.pycmd,
-            cmd_opts.port,
-            cmd_opts.colab,
-            cmd_opts.noparallel,
-            cmd_opts.noautoopen,
-            cmd_opts.dml,
-        )
-
-    # has_mps is only available in nightly pytorch (for now) and MasOS 12.3+.
-    # check `getattr` and try it for compatibility
-    @staticmethod
-    def has_mps() -> bool:
-        if not torch.backends.mps.is_available():
-            return False
-        try:
-            torch.zeros(1).to(torch.device("mps"))
-            return True
-        except Exception:
-            return False
-
-    @staticmethod
-    def has_xpu() -> bool:
-        if hasattr(torch, "xpu") and torch.xpu.is_available():
-            return True
-        else:
-            return False
-
-    def use_fp32_config(self):
-        for config_file in version_config_list:
-            self.json_config[config_file]["train"]["fp16_run"] = False
-            with open(f"configs/{config_file}", "r") as f:
-                strr = f.read().replace("true", "false")
-            with open(f"configs/{config_file}", "w") as f:
-                f.write(strr)
-        with open("infer/modules/train/preprocess.py", "r") as f:
-            strr = f.read().replace("3.7", "3.0")
-        with open("infer/modules/train/preprocess.py", "w") as f:
-            f.write(strr)
-        print("overwrite preprocess and configs.json")
-
-    def device_config(self) -> tuple:
-        if torch.cuda.is_available():
-            if self.has_xpu():
-                self.device = self.instead = "xpu:0"
-                self.is_half = True
-            i_device = int(self.device.split(":")[-1])
-            self.gpu_name = torch.cuda.get_device_name(i_device)
-            if (
-                ("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
-                or "P40" in self.gpu_name.upper()
-                or "P10" in self.gpu_name.upper()
-                or "1060" in self.gpu_name
-                or "1070" in self.gpu_name
-                or "1080" in self.gpu_name
-            ):
-                logger.info("Found GPU %s, force to fp32", self.gpu_name)
-                self.is_half = False
-                self.use_fp32_config()
-            else:
-                logger.info("Found GPU %s", self.gpu_name)
-            self.gpu_mem = int(
-                torch.cuda.get_device_properties(i_device).total_memory
-                / 1024
-                / 1024
-                / 1024
-                + 0.4
-            )
-            if self.gpu_mem <= 4:
-                with open("infer/modules/train/preprocess.py", "r") as f:
-                    strr = f.read().replace("3.7", "3.0")
-                with open("infer/modules/train/preprocess.py", "w") as f:
-                    f.write(strr)
-        elif self.has_mps():
-            logger.info("No supported Nvidia GPU found")
-            self.device = self.instead = "mps"
-            self.is_half = False
-            self.use_fp32_config()
-        else:
-            logger.info("No supported Nvidia GPU found")
-            self.device = self.instead = "cpu"
-            self.is_half = False
-            self.use_fp32_config()
-
-        if self.n_cpu == 0:
-            self.n_cpu = cpu_count()
-
-        if self.is_half:
-            # 6G显存配置
-            x_pad = 3
-            x_query = 10
-            x_center = 60
-            x_max = 65
-        else:
-            # 5G显存配置
-            x_pad = 1
-            x_query = 6
-            x_center = 38
-            x_max = 41
-
-        if self.gpu_mem is not None and self.gpu_mem <= 4:
-            x_pad = 1
-            x_query = 5
-            x_center = 30
-            x_max = 32
-        if self.dml:
-            logger.info("Use DirectML instead")
-            if (
-                os.path.exists(
-                    "runtime\Lib\site-packages\onnxruntime\capi\DirectML.dll"
-                )
-                == False
-            ):
-                try:
-                    os.rename(
-                        "runtime\Lib\site-packages\onnxruntime",
-                        "runtime\Lib\site-packages\onnxruntime-cuda",
-                    )
-                except:
-                    pass
-                try:
-                    os.rename(
-                        "runtime\Lib\site-packages\onnxruntime-dml",
-                        "runtime\Lib\site-packages\onnxruntime",
-                    )
-                except:
-                    pass
-            # if self.device != "cpu":
-            import torch_directml
-
-            self.device = torch_directml.device(torch_directml.default_device())
-            self.is_half = False
-        else:
-            if self.instead:
-                logger.info(f"Use {self.instead} instead")
-            if (
-                os.path.exists(
-                    "runtime\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"
-                )
-                == False
-            ):
-                try:
-                    os.rename(
-                        "runtime\Lib\site-packages\onnxruntime",
-                        "runtime\Lib\site-packages\onnxruntime-dml",
-                    )
-                except:
-                    pass
-                try:
-                    os.rename(
-                        "runtime\Lib\site-packages\onnxruntime-cuda",
-                        "runtime\Lib\site-packages\onnxruntime",
-                    )
-                except:
-                    pass
-        print("is_half:%s, device:%s" % (self.is_half, self.device))
-        return x_pad, x_query, x_center, x_max

configs/v1/32k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 32000,
-    "filter_length": 1024,
-    "hop_length": 320,
-    "win_length": 1024,
-    "n_mel_channels": 80,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,4,2,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/v1/40k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 40000,
-    "filter_length": 2048,
-    "hop_length": 400,
-    "win_length": 2048,
-    "n_mel_channels": 125,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/v1/48k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 11520,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 48000,
-    "filter_length": 2048,
-    "hop_length": 480,
-    "win_length": 2048,
-    "n_mel_channels": 128,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,6,2,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/v2/32k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 50,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.99975,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 100,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 32000,
-    "filter_length": 1024,
-    "hop_length": 320,
-    "win_length": 1024,
-    "n_mel_channels": 80,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,8,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [20,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/v2/40k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 50,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.99975,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 100,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 40000,
-    "filter_length": 2048,
-    "hop_length": 400,
-    "win_length": 2048,
-    "n_mel_channels": 125,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}

configs/v2/48k.json

@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 50,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.99975,
-    "segment_size": 17280,
-    "init_lr_ratio": 2,
-    "warmup_epochs": 100,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 48000,
-    "filter_length": 2048,
-    "hop_length": 480,
-    "win_length": 2048,
-    "n_mel_channels": 128,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [12,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [24,20,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}