xinference 1.10.0__py3-none-any.whl → 1.10.1__py3-none-any.whl

xinference/thirdparty/indextts/s2mel/dac/utils/__init__.py

@@ -0,0 +1,123 @@
+from pathlib import Path
+
+import argbind
+from audiotools import ml
+
+import indextts.s2mel.dac as dac
+
+DAC = dac.model.DAC
+Accelerator = ml.Accelerator
+
+__MODEL_LATEST_TAGS__ = {
+    ("44khz", "8kbps"): "0.0.1",
+    ("24khz", "8kbps"): "0.0.4",
+    ("16khz", "8kbps"): "0.0.5",
+    ("44khz", "16kbps"): "1.0.0",
+}
+
+__MODEL_URLS__ = {
+    (
+        "44khz",
+        "0.0.1",
+        "8kbps",
+    ): "https://github.com/descriptinc/descript-audio-codec/releases/download/0.0.1/weights.pth",
+    (
+        "24khz",
+        "0.0.4",
+        "8kbps",
+    ): "https://github.com/descriptinc/descript-audio-codec/releases/download/0.0.4/weights_24khz.pth",
+    (
+        "16khz",
+        "0.0.5",
+        "8kbps",
+    ): "https://github.com/descriptinc/descript-audio-codec/releases/download/0.0.5/weights_16khz.pth",
+    (
+        "44khz",
+        "1.0.0",
+        "16kbps",
+    ): "https://github.com/descriptinc/descript-audio-codec/releases/download/1.0.0/weights_44khz_16kbps.pth",
+}
+
+
+@argbind.bind(group="download", positional=True, without_prefix=True)
+def download(
+    model_type: str = "44khz", model_bitrate: str = "8kbps", tag: str = "latest"
+):
+    """
+    Function that downloads the weights file from URL if a local cache is not found.
+
+    Parameters
+    ----------
+    model_type : str
+        The type of model to download. Must be one of "44khz", "24khz", or "16khz". Defaults to "44khz".
+    model_bitrate: str
+        Bitrate of the model. Must be one of "8kbps", or "16kbps". Defaults to "8kbps".
+        Only 44khz model supports 16kbps.
+    tag : str
+        The tag of the model to download. Defaults to "latest".
+
+    Returns
+    -------
+    Path
+        Directory path required to load model via audiotools.
+    """
+    model_type = model_type.lower()
+    tag = tag.lower()
+
+    assert model_type in [
+        "44khz",
+        "24khz",
+        "16khz",
+    ], "model_type must be one of '44khz', '24khz', or '16khz'"
+
+    assert model_bitrate in [
+        "8kbps",
+        "16kbps",
+    ], "model_bitrate must be one of '8kbps', or '16kbps'"
+
+    if tag == "latest":
+        tag = __MODEL_LATEST_TAGS__[(model_type, model_bitrate)]
+
+    download_link = __MODEL_URLS__.get((model_type, tag, model_bitrate), None)
+
+    if download_link is None:
+        raise ValueError(
+            f"Could not find model with tag {tag} and model type {model_type}"
+        )
+
+    local_path = (
+        Path.home()
+        / ".cache"
+        / "descript"
+        / "dac"
+        / f"weights_{model_type}_{model_bitrate}_{tag}.pth"
+    )
+    if not local_path.exists():
+        local_path.parent.mkdir(parents=True, exist_ok=True)
+
+        # Download the model
+        import requests
+
+        response = requests.get(download_link)
+
+        if response.status_code != 200:
+            raise ValueError(
+                f"Could not download model. Received response code {response.status_code}"
+            )
+        local_path.write_bytes(response.content)
+
+    return local_path
+
+
+def load_model(
+    model_type: str = "44khz",
+    model_bitrate: str = "8kbps",
+    tag: str = "latest",
+    load_path: str = None,
+):
+    if not load_path:
+        load_path = download(
+            model_type=model_type, model_bitrate=model_bitrate, tag=tag
+        )
+    generator = DAC.load(load_path)
+    return generator

xinference/thirdparty/indextts/s2mel/dac/utils/decode.py

@@ -0,0 +1,95 @@
+import warnings
+from pathlib import Path
+
+import argbind
+import numpy as np
+import torch
+from audiotools import AudioSignal
+from tqdm import tqdm
+
+from dac import DACFile
+from dac.utils import load_model
+
+warnings.filterwarnings("ignore", category=UserWarning)
+
+
+@argbind.bind(group="decode", positional=True, without_prefix=True)
+@torch.inference_mode()
+@torch.no_grad()
+def decode(
+    input: str,
+    output: str = "",
+    weights_path: str = "",
+    model_tag: str = "latest",
+    model_bitrate: str = "8kbps",
+    device: str = "cuda",
+    model_type: str = "44khz",
+    verbose: bool = False,
+):
+    """Decode audio from codes.
+
+    Parameters
+    ----------
+    input : str
+        Path to input directory or file
+    output : str, optional
+        Path to output directory, by default "".
+        If `input` is a directory, the directory sub-tree relative to `input` is re-created in `output`.
+    weights_path : str, optional
+        Path to weights file, by default "". If not specified, the weights file will be downloaded from the internet using the
+        model_tag and model_type.
+    model_tag : str, optional
+        Tag of the model to use, by default "latest". Ignored if `weights_path` is specified.
+    model_bitrate: str
+        Bitrate of the model. Must be one of "8kbps", or "16kbps". Defaults to "8kbps".
+    device : str, optional
+        Device to use, by default "cuda". If "cpu", the model will be loaded on the CPU.
+    model_type : str, optional
+        The type of model to use. Must be one of "44khz", "24khz", or "16khz". Defaults to "44khz". Ignored if `weights_path` is specified.
+    """
+    generator = load_model(
+        model_type=model_type,
+        model_bitrate=model_bitrate,
+        tag=model_tag,
+        load_path=weights_path,
+    )
+    generator.to(device)
+    generator.eval()
+
+    # Find all .dac files in input directory
+    _input = Path(input)
+    input_files = list(_input.glob("**/*.dac"))
+
+    # If input is a .dac file, add it to the list
+    if _input.suffix == ".dac":
+        input_files.append(_input)
+
+    # Create output directory
+    output = Path(output)
+    output.mkdir(parents=True, exist_ok=True)
+
+    for i in tqdm(range(len(input_files)), desc=f"Decoding files"):
+        # Load file
+        artifact = DACFile.load(input_files[i])
+
+        # Reconstruct audio from codes
+        recons = generator.decompress(artifact, verbose=verbose)
+
+        # Compute output path
+        relative_path = input_files[i].relative_to(input)
+        output_dir = output / relative_path.parent
+        if not relative_path.name:
+            output_dir = output
+            relative_path = input_files[i]
+        output_name = relative_path.with_suffix(".wav").name
+        output_path = output_dir / output_name
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+
+        # Write to file
+        recons.write(output_path)
+
+
+if __name__ == "__main__":
+    args = argbind.parse_args()
+    with argbind.scope(args):
+        decode()

xinference/thirdparty/indextts/s2mel/dac/utils/encode.py

@@ -0,0 +1,94 @@
+import math
+import warnings
+from pathlib import Path
+
+import argbind
+import numpy as np
+import torch
+from audiotools import AudioSignal
+from audiotools.core import util
+from tqdm import tqdm
+
+from dac.utils import load_model
+
+warnings.filterwarnings("ignore", category=UserWarning)
+
+
+@argbind.bind(group="encode", positional=True, without_prefix=True)
+@torch.inference_mode()
+@torch.no_grad()
+def encode(
+    input: str,
+    output: str = "",
+    weights_path: str = "",
+    model_tag: str = "latest",
+    model_bitrate: str = "8kbps",
+    n_quantizers: int = None,
+    device: str = "cuda",
+    model_type: str = "44khz",
+    win_duration: float = 5.0,
+    verbose: bool = False,
+):
+    """Encode audio files in input path to .dac format.
+
+    Parameters
+    ----------
+    input : str
+        Path to input audio file or directory
+    output : str, optional
+        Path to output directory, by default "". If `input` is a directory, the directory sub-tree relative to `input` is re-created in `output`.
+    weights_path : str, optional
+        Path to weights file, by default "". If not specified, the weights file will be downloaded from the internet using the
+        model_tag and model_type.
+    model_tag : str, optional
+        Tag of the model to use, by default "latest". Ignored if `weights_path` is specified.
+    model_bitrate: str
+        Bitrate of the model. Must be one of "8kbps", or "16kbps". Defaults to "8kbps".
+    n_quantizers : int, optional
+        Number of quantizers to use, by default None. If not specified, all the quantizers will be used and the model will compress at maximum bitrate.
+    device : str, optional
+        Device to use, by default "cuda"
+    model_type : str, optional
+        The type of model to use. Must be one of "44khz", "24khz", or "16khz". Defaults to "44khz". Ignored if `weights_path` is specified.
+    """
+    generator = load_model(
+        model_type=model_type,
+        model_bitrate=model_bitrate,
+        tag=model_tag,
+        load_path=weights_path,
+    )
+    generator.to(device)
+    generator.eval()
+    kwargs = {"n_quantizers": n_quantizers}
+
+    # Find all audio files in input path
+    input = Path(input)
+    audio_files = util.find_audio(input)
+
+    output = Path(output)
+    output.mkdir(parents=True, exist_ok=True)
+
+    for i in tqdm(range(len(audio_files)), desc="Encoding files"):
+        # Load file
+        signal = AudioSignal(audio_files[i])
+
+        # Encode audio to .dac format
+        artifact = generator.compress(signal, win_duration, verbose=verbose, **kwargs)
+
+        # Compute output path
+        relative_path = audio_files[i].relative_to(input)
+        output_dir = output / relative_path.parent
+        if not relative_path.name:
+            output_dir = output
+            relative_path = audio_files[i]
+        output_name = relative_path.with_suffix(".dac").name
+        output_path = output_dir / output_name
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+
+        artifact.save(output_path)
+
+
+if __name__ == "__main__":
+    args = argbind.parse_args()
+    with argbind.scope(args):
+        encode()

xinference/thirdparty/indextts/s2mel/hf_utils.py

@@ -0,0 +1,12 @@
+import os
+from huggingface_hub import hf_hub_download
+
+
+def load_custom_model_from_hf(repo_id, model_filename="pytorch_model.bin", config_filename="config.yml"):
+    os.makedirs("./checkpoints", exist_ok=True)
+    model_path = hf_hub_download(repo_id=repo_id, filename=model_filename, cache_dir="./checkpoints")
+    if config_filename is None:
+        return model_path
+    config_path = hf_hub_download(repo_id=repo_id, filename=config_filename, cache_dir="./checkpoints")
+
+    return model_path, config_path

xinference/thirdparty/indextts/s2mel/modules/alias_free_torch/__init__.py

@@ -0,0 +1,5 @@
+# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
+
+from .filter import *
+from .resample import *
+from .act import *

xinference/thirdparty/indextts/s2mel/modules/alias_free_torch/act.py

@@ -0,0 +1,29 @@
+# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
+
+import torch.nn as nn
+from .resample import UpSample1d, DownSample1d
+
+
+class Activation1d(nn.Module):
+    def __init__(
+        self,
+        activation,
+        up_ratio: int = 2,
+        down_ratio: int = 2,
+        up_kernel_size: int = 12,
+        down_kernel_size: int = 12,
+    ):
+        super().__init__()
+        self.up_ratio = up_ratio
+        self.down_ratio = down_ratio
+        self.act = activation
+        self.upsample = UpSample1d(up_ratio, up_kernel_size)
+        self.downsample = DownSample1d(down_ratio, down_kernel_size)
+
+    # x: [B,C,T]
+    def forward(self, x):
+        x = self.upsample(x)
+        x = self.act(x)
+        x = self.downsample(x)
+
+        return x

xinference/thirdparty/indextts/s2mel/modules/alias_free_torch/filter.py

@@ -0,0 +1,96 @@
+# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import math
+
+if "sinc" in dir(torch):
+    sinc = torch.sinc
+else:
+    # This code is adopted from adefossez's julius.core.sinc under the MIT License
+    # https://adefossez.github.io/julius/julius/core.html
+    def sinc(x: torch.Tensor):
+        """
+        Implementation of sinc, i.e. sin(pi * x) / (pi * x)
+        __Warning__: Different to julius.sinc, the input is multiplied by `pi`!
+        """
+        return torch.where(
+            x == 0,
+            torch.tensor(1.0, device=x.device, dtype=x.dtype),
+            torch.sin(math.pi * x) / math.pi / x,
+        )
+
+
+# This code is adopted from adefossez's julius.lowpass.LowPassFilters under the MIT License
+# https://adefossez.github.io/julius/julius/lowpass.html
+def kaiser_sinc_filter1d(
+    cutoff, half_width, kernel_size
+):  # return filter [1,1,kernel_size]
+    even = kernel_size % 2 == 0
+    half_size = kernel_size // 2
+
+    # For kaiser window
+    delta_f = 4 * half_width
+    A = 2.285 * (half_size - 1) * math.pi * delta_f + 7.95
+    if A > 50.0:
+        beta = 0.1102 * (A - 8.7)
+    elif A >= 21.0:
+        beta = 0.5842 * (A - 21) ** 0.4 + 0.07886 * (A - 21.0)
+    else:
+        beta = 0.0
+    window = torch.kaiser_window(kernel_size, beta=beta, periodic=False)
+
+    # ratio = 0.5/cutoff -> 2 * cutoff = 1 / ratio
+    if even:
+        time = torch.arange(-half_size, half_size) + 0.5
+    else:
+        time = torch.arange(kernel_size) - half_size
+    if cutoff == 0:
+        filter_ = torch.zeros_like(time)
+    else:
+        filter_ = 2 * cutoff * window * sinc(2 * cutoff * time)
+        # Normalize filter to have sum = 1, otherwise we will have a small leakage
+        # of the constant component in the input signal.
+        filter_ /= filter_.sum()
+        filter = filter_.view(1, 1, kernel_size)
+
+    return filter
+
+
+class LowPassFilter1d(nn.Module):
+    def __init__(
+        self,
+        cutoff=0.5,
+        half_width=0.6,
+        stride: int = 1,
+        padding: bool = True,
+        padding_mode: str = "replicate",
+        kernel_size: int = 12,
+    ):
+        # kernel_size should be even number for stylegan3 setup,
+        # in this implementation, odd number is also possible.
+        super().__init__()
+        if cutoff < -0.0:
+            raise ValueError("Minimum cutoff must be larger than zero.")
+        if cutoff > 0.5:
+            raise ValueError("A cutoff above 0.5 does not make sense.")
+        self.kernel_size = kernel_size
+        self.even = kernel_size % 2 == 0
+        self.pad_left = kernel_size // 2 - int(self.even)
+        self.pad_right = kernel_size // 2
+        self.stride = stride
+        self.padding = padding
+        self.padding_mode = padding_mode
+        filter = kaiser_sinc_filter1d(cutoff, half_width, kernel_size)
+        self.register_buffer("filter", filter)
+
+    # input [B, C, T]
+    def forward(self, x):
+        _, C, _ = x.shape
+
+        if self.padding:
+            x = F.pad(x, (self.pad_left, self.pad_right), mode=self.padding_mode)
+        out = F.conv1d(x, self.filter.expand(C, -1, -1), stride=self.stride, groups=C)
+
+        return out

xinference/thirdparty/indextts/s2mel/modules/alias_free_torch/resample.py

@@ -0,0 +1,57 @@
+# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
+
+import torch.nn as nn
+from torch.nn import functional as F
+from .filter import LowPassFilter1d
+from .filter import kaiser_sinc_filter1d
+
+
+class UpSample1d(nn.Module):
+    def __init__(self, ratio=2, kernel_size=None):
+        super().__init__()
+        self.ratio = ratio
+        self.kernel_size = (
+            int(6 * ratio // 2) * 2 if kernel_size is None else kernel_size
+        )
+        self.stride = ratio
+        self.pad = self.kernel_size // ratio - 1
+        self.pad_left = self.pad * self.stride + (self.kernel_size - self.stride) // 2
+        self.pad_right = (
+            self.pad * self.stride + (self.kernel_size - self.stride + 1) // 2
+        )
+        filter = kaiser_sinc_filter1d(
+            cutoff=0.5 / ratio, half_width=0.6 / ratio, kernel_size=self.kernel_size
+        )
+        self.register_buffer("filter", filter)
+
+    # x: [B, C, T]
+    def forward(self, x):
+        _, C, _ = x.shape
+
+        x = F.pad(x, (self.pad, self.pad), mode="replicate")
+        x = self.ratio * F.conv_transpose1d(
+            x, self.filter.expand(C, -1, -1), stride=self.stride, groups=C
+        )
+        x = x[..., self.pad_left : -self.pad_right]
+
+        return x
+
+
+class DownSample1d(nn.Module):
+    def __init__(self, ratio=2, kernel_size=None):
+        super().__init__()
+        self.ratio = ratio
+        self.kernel_size = (
+            int(6 * ratio // 2) * 2 if kernel_size is None else kernel_size
+        )
+        self.lowpass = LowPassFilter1d(
+            cutoff=0.5 / ratio,
+            half_width=0.6 / ratio,
+            stride=ratio,
+            kernel_size=self.kernel_size,
+        )
+
+    def forward(self, x):
+        xx = self.lowpass(x)
+
+        return xx

xinference/thirdparty/indextts/s2mel/modules/audio.py

@@ -0,0 +1,82 @@
+import numpy as np
+import torch
+import torch.utils.data
+from librosa.filters import mel as librosa_mel_fn
+from scipy.io.wavfile import read
+
+MAX_WAV_VALUE = 32768.0
+
+
+def load_wav(full_path):
+    sampling_rate, data = read(full_path)
+    return data, sampling_rate
+
+
+def dynamic_range_compression(x, C=1, clip_val=1e-5):
+    return np.log(np.clip(x, a_min=clip_val, a_max=None) * C)
+
+
+def dynamic_range_decompression(x, C=1):
+    return np.exp(x) / C
+
+
+def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
+    return torch.log(torch.clamp(x, min=clip_val) * C)
+
+
+def dynamic_range_decompression_torch(x, C=1):
+    return torch.exp(x) / C
+
+
+def spectral_normalize_torch(magnitudes):
+    output = dynamic_range_compression_torch(magnitudes)
+    return output
+
+
+def spectral_de_normalize_torch(magnitudes):
+    output = dynamic_range_decompression_torch(magnitudes)
+    return output
+
+
+mel_basis = {}
+hann_window = {}
+
+
+def mel_spectrogram(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False):
+#     if torch.min(y) < -1.0:
+#         print("min value is ", torch.min(y))
+#     if torch.max(y) > 1.0:
+#         print("max value is ", torch.max(y))
+
+    global mel_basis, hann_window  # pylint: disable=global-statement
+    if f"{str(sampling_rate)}_{str(fmax)}_{str(y.device)}" not in mel_basis:
+        mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax)
+        mel_basis[str(sampling_rate) + "_" + str(fmax) + "_" + str(y.device)] = torch.from_numpy(mel).float().to(y.device)
+        hann_window[str(sampling_rate) + "_" + str(y.device)] = torch.hann_window(win_size).to(y.device)
+
+    y = torch.nn.functional.pad(
+        y.unsqueeze(1), (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)), mode="reflect"
+    )
+    y = y.squeeze(1)
+
+    spec = torch.view_as_real(
+        torch.stft(
+            y,
+            n_fft,
+            hop_length=hop_size,
+            win_length=win_size,
+            window=hann_window[str(sampling_rate) + "_" + str(y.device)],
+            center=center,
+            pad_mode="reflect",
+            normalized=False,
+            onesided=True,
+            return_complex=True,
+        )
+    )
+
+    spec = torch.sqrt(spec.pow(2).sum(-1) + (1e-9))
+
+    spec = torch.matmul(mel_basis[str(sampling_rate) + "_" + str(fmax) + "_" + str(y.device)], spec)
+    spec = spectral_normalize_torch(spec)
+
+    return spec