File size: 3,623 Bytes
ee21b96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
#!/usr/bin/env python3
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

import argparse
import logging
from pathlib import Path
import shutil
from tempfile import NamedTemporaryFile

import pandas as pd
from examples.speech_to_text.data_utils import (
    create_zip,
    extract_fbank_features,
    gen_config_yaml,
    gen_vocab,
    get_zip_manifest,
    save_df_to_tsv,
)
from torchaudio.datasets import LIBRISPEECH
from tqdm import tqdm


log = logging.getLogger(__name__)

SPLITS = [
    "train-clean-100",
    "train-clean-360",
    "train-other-500",
    "dev-clean",
    "dev-other",
    "test-clean",
    "test-other",
]

MANIFEST_COLUMNS = ["id", "audio", "n_frames", "tgt_text", "speaker"]


def process(args):
    out_root = Path(args.output_root).absolute()
    out_root.mkdir(exist_ok=True)
    # Extract features
    feature_root = out_root / "fbank80"
    feature_root.mkdir(exist_ok=True)
    for split in SPLITS:
        print(f"Fetching split {split}...")
        dataset = LIBRISPEECH(out_root.as_posix(), url=split, download=True)
        print("Extracting log mel filter bank features...")
        for wav, sample_rate, _, spk_id, chapter_no, utt_no in tqdm(dataset):
            sample_id = f"{spk_id}-{chapter_no}-{utt_no}"
            extract_fbank_features(
                wav, sample_rate, feature_root / f"{sample_id}.npy"
            )
    # Pack features into ZIP
    zip_path = out_root / "fbank80.zip"
    print("ZIPing features...")
    create_zip(feature_root, zip_path)
    print("Fetching ZIP manifest...")
    audio_paths, audio_lengths = get_zip_manifest(zip_path)
    # Generate TSV manifest
    print("Generating manifest...")
    train_text = []
    for split in SPLITS:
        manifest = {c: [] for c in MANIFEST_COLUMNS}
        dataset = LIBRISPEECH(out_root.as_posix(), url=split)
        for _, _, utt, spk_id, chapter_no, utt_no in tqdm(dataset):
            sample_id = f"{spk_id}-{chapter_no}-{utt_no}"
            manifest["id"].append(sample_id)
            manifest["audio"].append(audio_paths[sample_id])
            manifest["n_frames"].append(audio_lengths[sample_id])
            manifest["tgt_text"].append(utt.lower())
            manifest["speaker"].append(spk_id)
        save_df_to_tsv(
            pd.DataFrame.from_dict(manifest), out_root / f"{split}.tsv"
        )
        if split.startswith("train"):
            train_text.extend(manifest["tgt_text"])
    # Generate vocab
    vocab_size = "" if args.vocab_type == "char" else str(args.vocab_size)
    spm_filename_prefix = f"spm_{args.vocab_type}{vocab_size}"
    with NamedTemporaryFile(mode="w") as f:
        for t in train_text:
            f.write(t + "\n")
        gen_vocab(
            Path(f.name),
            out_root / spm_filename_prefix,
            args.vocab_type,
            args.vocab_size,
        )
    # Generate config YAML
    gen_config_yaml(
        out_root,
        spm_filename=spm_filename_prefix + ".model",
        specaugment_policy="ld"
    )
    # Clean up
    shutil.rmtree(feature_root)


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--output-root", "-o", required=True, type=str)
    parser.add_argument(
        "--vocab-type",
        default="unigram",
        required=True,
        type=str,
        choices=["bpe", "unigram", "char"],
    ),
    parser.add_argument("--vocab-size", default=10000, type=int)
    args = parser.parse_args()

    process(args)


if __name__ == "__main__":
    main()