mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
735fb9a73d
* init * isort formatted * minor updates * Create shared * Update prepare_tokens_vctk.py * Update prepare_tokens_vctk.py * Update prepare_tokens_vctk.py * Update prepare.sh * updated * Update train.py * Update train.py * Update tts_datamodule.py * Update train.py * Update train.py * Update train.py * Update train.py * Update train.py * Update train.py * fixed formatting issue * Update infer.py * removed redundant files * Create monotonic_align * removed redundant files * created symlinks * Update prepare.sh * minor adjustments * Create requirements_tts.txt * Update requirements_tts.txt added version constraints * Update infer.py * Update infer.py * Update infer.py * updated docs * Update export-onnx.py * Update export-onnx.py * Update test_onnx.py * updated requirements.txt * Update test_onnx.py * Update test_onnx.py * docs updated * docs fixed * minor updates
62 lines
2.0 KiB
Python
Executable File
62 lines
2.0 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
# Copyright 2023 Xiaomi Corp. (authors: Zengwei Yao,
|
|
# Zengrui Jin,)
|
|
#
|
|
# See ../../../../LICENSE for clarification regarding multiple authors
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
|
|
"""
|
|
This file reads the texts in given manifest and save the new cuts with phoneme tokens.
|
|
"""
|
|
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
import g2p_en
|
|
import tacotron_cleaner.cleaners
|
|
from lhotse import CutSet, load_manifest
|
|
from tqdm.auto import tqdm
|
|
|
|
|
|
def prepare_tokens_vctk():
|
|
output_dir = Path("data/spectrogram")
|
|
prefix = "vctk"
|
|
suffix = "jsonl.gz"
|
|
partition = "all"
|
|
|
|
cut_set = load_manifest(output_dir / f"{prefix}_cuts_{partition}.{suffix}")
|
|
g2p = g2p_en.G2p()
|
|
|
|
new_cuts = []
|
|
for cut in tqdm(cut_set):
|
|
# Each cut only contains one supervision
|
|
assert len(cut.supervisions) == 1, len(cut.supervisions)
|
|
text = cut.supervisions[0].text
|
|
# Text normalization
|
|
text = tacotron_cleaner.cleaners.custom_english_cleaners(text)
|
|
# Convert to phonemes
|
|
cut.tokens = g2p(text)
|
|
new_cuts.append(cut)
|
|
|
|
new_cut_set = CutSet.from_cuts(new_cuts)
|
|
new_cut_set.to_file(output_dir / f"{prefix}_cuts_with_tokens_{partition}.{suffix}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
formatter = "%(asctime)s %(levelname)s [%(filename)s:%(lineno)d] %(message)s"
|
|
logging.basicConfig(format=formatter, level=logging.INFO)
|
|
|
|
prepare_tokens_vctk()
|