Merge pull request #121 from jimregan/english-data

ljspeech/hificaptain from #99

matcha/utils/data/hificaptain.py

@@ -0,0 +1,148 @@
+#!/usr/bin/env python
+import argparse
+import os
+import sys
+import tempfile
+from pathlib import Path
+
+import torchaudio
+from torch.hub import download_url_to_file
+from tqdm import tqdm
+
+from matcha.utils.data.utils import _extract_zip
+
+URLS = {
+    "en-US": {
+        "female": "https://ast-astrec.nict.go.jp/release/hi-fi-captain/hfc_en-US_F.zip",
+        "male": "https://ast-astrec.nict.go.jp/release/hi-fi-captain/hfc_en-US_M.zip",
+    },
+    "ja-JP": {
+        "female": "https://ast-astrec.nict.go.jp/release/hi-fi-captain/hfc_ja-JP_F.zip",
+        "male": "https://ast-astrec.nict.go.jp/release/hi-fi-captain/hfc_ja-JP_M.zip",
+    },
+}
+
+INFO_PAGE = "https://ast-astrec.nict.go.jp/en/release/hi-fi-captain/"
+
+# On their website they say "We NICT open-sourced Hi-Fi-CAPTAIN",
+# but they use this very-much-not-open-source licence.
+# Dunno if this is open washing or stupidity.
+LICENCE = "CC BY-NC-SA 4.0"
+
+# I'd normally put the citation here. It's on their website.
+# Boo to non-open-source stuff.
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("-s", "--save-dir", type=str, default=None, help="Place to store the downloaded zip files")
+    parser.add_argument(
+        "-r",
+        "--skip-resampling",
+        action="store_true",
+        default=False,
+        help="Skip resampling the data (from 48 to 22.05)",
+    )
+    parser.add_argument(
+        "-l", "--language", type=str, choices=["en-US", "ja-JP"], default="en-US", help="The language to download"
+    )
+    parser.add_argument(
+        "-g",
+        "--gender",
+        type=str,
+        choices=["male", "female"],
+        default="female",
+        help="The gender of the speaker to download",
+    )
+    parser.add_argument(
+        "-o",
+        "--output_dir",
+        type=str,
+        default="data",
+        help="Place to store the converted data. Top-level only, the subdirectory will be created",
+    )
+
+    return parser.parse_args()
+
+
+def process_text(infile, outpath: Path):
+    outmode = "w"
+    if infile.endswith("dev.txt"):
+        outfile = outpath / "valid.txt"
+    elif infile.endswith("eval.txt"):
+        outfile = outpath / "test.txt"
+    else:
+        outfile = outpath / "train.txt"
+        if outfile.exists():
+            outmode = "a"
+    with (
+        open(infile, encoding="utf-8") as inf,
+        open(outfile, outmode, encoding="utf-8") as of,
+    ):
+        for line in inf.readlines():
+            line = line.strip()
+            fileid, rest = line.split(" ", maxsplit=1)
+            outfile = str(outpath / f"{fileid}.wav")
+            of.write(f"{outfile}|{rest}\n")
+
+
+def process_files(zipfile, outpath, resample=True):
+    with tempfile.TemporaryDirectory() as tmpdirname:
+        for filename in tqdm(_extract_zip(zipfile, tmpdirname)):
+            if not filename.startswith(tmpdirname):
+                filename = os.path.join(tmpdirname, filename)
+            if filename.endswith(".txt"):
+                process_text(filename, outpath)
+            elif filename.endswith(".wav"):
+                filepart = filename.rsplit("/", maxsplit=1)[-1]
+                outfile = str(outpath / filepart)
+                arr, sr = torchaudio.load(filename)
+                if resample:
+                    arr = torchaudio.functional.resample(arr, orig_freq=sr, new_freq=22050)
+                torchaudio.save(outfile, arr, 22050)
+            else:
+                continue
+
+
+def main():
+    args = get_args()
+
+    save_dir = None
+    if args.save_dir:
+        save_dir = Path(args.save_dir)
+        if not save_dir.is_dir():
+            save_dir.mkdir()
+
+    if not args.output_dir:
+        print("output directory not specified, exiting")
+        sys.exit(1)
+
+    URL = URLS[args.language][args.gender]
+    dirname = f"hi-fi_{args.language}_{args.gender}"
+
+    outbasepath = Path(args.output_dir)
+    if not outbasepath.is_dir():
+        outbasepath.mkdir()
+    outpath = outbasepath / dirname
+    if not outpath.is_dir():
+        outpath.mkdir()
+
+    resample = True
+    if args.skip_resampling:
+        resample = False
+
+    if save_dir:
+        zipname = URL.rsplit("/", maxsplit=1)[-1]
+        zipfile = save_dir / zipname
+        if not zipfile.exists():
+            download_url_to_file(URL, zipfile, progress=True)
+        process_files(zipfile, outpath, resample)
+    else:
+        with tempfile.NamedTemporaryFile(suffix=".zip", delete=True) as zf:
+            download_url_to_file(URL, zf.name, progress=True)
+            process_files(zf.name, outpath, resample)
+
+
+if __name__ == "__main__":
+    main()

matcha/utils/data/ljspeech.py

@@ -0,0 +1,97 @@
+#!/usr/bin/env python
+import argparse
+import random
+import tempfile
+from pathlib import Path
+
+from torch.hub import download_url_to_file
+
+from matcha.utils.data.utils import _extract_tar
+
+URL = "https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2"
+
+INFO_PAGE = "https://keithito.com/LJ-Speech-Dataset/"
+
+LICENCE = "Public domain (LibriVox copyright disclaimer)"
+
+CITATION = """
+@misc{ljspeech17,
+  author       = {Keith Ito and Linda Johnson},
+  title        = {The LJ Speech Dataset},
+  howpublished = {\\url{https://keithito.com/LJ-Speech-Dataset/}},
+  year         = 2017
+}
+"""
+
+
+def decision():
+    return random.random() < 0.98
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("-s", "--save-dir", type=str, default=None, help="Place to store the downloaded zip files")
+    parser.add_argument(
+        "output_dir",
+        type=str,
+        nargs="?",
+        default="data",
+        help="Place to store the converted data (subdirectory LJSpeech-1.1 will be created)",
+    )
+
+    return parser.parse_args()
+
+
+def process_csv(ljpath: Path):
+    if (ljpath / "metadata.csv").exists():
+        basepath = ljpath
+    elif (ljpath / "LJSpeech-1.1" / "metadata.csv").exists():
+        basepath = ljpath / "LJSpeech-1.1"
+    csvpath = basepath / "metadata.csv"
+    wavpath = basepath / "wavs"
+
+    with (
+        open(csvpath, encoding="utf-8") as csvf,
+        open(basepath / "train.txt", "w", encoding="utf-8") as tf,
+        open(basepath / "val.txt", "w", encoding="utf-8") as vf,
+    ):
+        for line in csvf.readlines():
+            line = line.strip()
+            parts = line.split("|")
+            wavfile = str(wavpath / f"{parts[0]}.wav")
+            if decision():
+                tf.write(f"{wavfile}|{parts[1]}\n")
+            else:
+                vf.write(f"{wavfile}|{parts[1]}\n")
+
+
+def main():
+    args = get_args()
+
+    save_dir = None
+    if args.save_dir:
+        save_dir = Path(args.save_dir)
+        if not save_dir.is_dir():
+            save_dir.mkdir()
+
+    outpath = Path(args.output_dir)
+    if not outpath.is_dir():
+        outpath.mkdir()
+
+    if save_dir:
+        tarname = URL.rsplit("/", maxsplit=1)[-1]
+        tarfile = save_dir / tarname
+        if not tarfile.exists():
+            download_url_to_file(URL, str(tarfile), progress=True)
+        _extract_tar(tarfile, outpath)
+        process_csv(outpath)
+    else:
+        with tempfile.NamedTemporaryFile(suffix=".tar.bz2", delete=True) as zf:
+            download_url_to_file(URL, zf.name, progress=True)
+            _extract_tar(zf.name, outpath)
+            process_csv(outpath)
+
+
+if __name__ == "__main__":
+    main()

matcha/utils/data/utils.py

@@ -0,0 +1,53 @@
+# taken from https://github.com/pytorch/audio/blob/main/src/torchaudio/datasets/utils.py
+# Copyright (c) 2017 Facebook Inc. (Soumith Chintala)
+# Licence: BSD 2-Clause
+# pylint: disable=C0123
+
+import logging
+import os
+import tarfile
+import zipfile
+from pathlib import Path
+from typing import Any, List, Optional, Union
+
+_LG = logging.getLogger(__name__)
+
+
+def _extract_tar(from_path: Union[str, Path], to_path: Optional[str] = None, overwrite: bool = False) -> List[str]:
+    if type(from_path) is Path:
+        from_path = str(Path)
+
+    if to_path is None:
+        to_path = os.path.dirname(from_path)
+
+    with tarfile.open(from_path, "r") as tar:
+        files = []
+        for file_ in tar:  # type: Any
+            file_path = os.path.join(to_path, file_.name)
+            if file_.isfile():
+                files.append(file_path)
+                if os.path.exists(file_path):
+                    _LG.info("%s already extracted.", file_path)
+                    if not overwrite:
+                        continue
+            tar.extract(file_, to_path)
+        return files
+
+
+def _extract_zip(from_path: Union[str, Path], to_path: Optional[str] = None, overwrite: bool = False) -> List[str]:
+    if type(from_path) is Path:
+        from_path = str(Path)
+
+    if to_path is None:
+        to_path = os.path.dirname(from_path)
+
+    with zipfile.ZipFile(from_path, "r") as zfile:
+        files = zfile.namelist()
+        for file_ in files:
+            file_path = os.path.join(to_path, file_)
+            if os.path.exists(file_path):
+                _LG.info("%s already extracted.", file_path)
+                if not overwrite:
+                    continue
+            zfile.extract(file_, to_path)
+    return files