refactor: rename canto-backend → backend, canto-frontend → frontend
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
123
backend/indextts/s2mel/dac/utils/__init__.py
Normal file
123
backend/indextts/s2mel/dac/utils/__init__.py
Normal file
@@ -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
|
||||
95
backend/indextts/s2mel/dac/utils/decode.py
Normal file
95
backend/indextts/s2mel/dac/utils/decode.py
Normal file
@@ -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()
|
||||
94
backend/indextts/s2mel/dac/utils/encode.py
Normal file
94
backend/indextts/s2mel/dac/utils/encode.py
Normal file
@@ -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()
|
||||
Reference in New Issue
Block a user