mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 10:02:22 +00:00
0622dea30d
* first commit * replace phonimizer with g2p * use Conformer as text encoder * modify training script, clean codes * rename directory * convert text to tokens in data preparation stage * fix tts_datamodule.py * support onnx export and testing the exported onnx model * add doc * add README.md * fix style
74 lines
3.9 KiB
Python
Executable File
74 lines
3.9 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
# Copyright 2023 Xiaomi Corp. (authors: Zengwei Yao)
|
|
#
|
|
# 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 displays duration statistics of utterances in a manifest.
|
|
You can use the displayed value to choose minimum/maximum duration
|
|
to remove short and long utterances during the training.
|
|
|
|
See the function `remove_short_and_long_utt()` in vits/train.py
|
|
for usage.
|
|
"""
|
|
|
|
|
|
from lhotse import load_manifest_lazy
|
|
|
|
|
|
def main():
|
|
path = "./data/spectrogram/ljspeech_cuts_all.jsonl.gz"
|
|
cuts = load_manifest_lazy(path)
|
|
cuts.describe()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|
|
|
|
"""
|
|
Cut statistics:
|
|
╒═══════════════════════════╤══════════╕
|
|
│ Cuts count: │ 13100 │
|
|
├───────────────────────────┼──────────┤
|
|
│ Total duration (hh:mm:ss) │ 23:55:18 │
|
|
├───────────────────────────┼──────────┤
|
|
│ mean │ 6.6 │
|
|
├───────────────────────────┼──────────┤
|
|
│ std │ 2.2 │
|
|
├───────────────────────────┼──────────┤
|
|
│ min │ 1.1 │
|
|
├───────────────────────────┼──────────┤
|
|
│ 25% │ 5.0 │
|
|
├───────────────────────────┼──────────┤
|
|
│ 50% │ 6.8 │
|
|
├───────────────────────────┼──────────┤
|
|
│ 75% │ 8.4 │
|
|
├───────────────────────────┼──────────┤
|
|
│ 99% │ 10.0 │
|
|
├───────────────────────────┼──────────┤
|
|
│ 99.5% │ 10.1 │
|
|
├───────────────────────────┼──────────┤
|
|
│ 99.9% │ 10.1 │
|
|
├───────────────────────────┼──────────┤
|
|
│ max │ 10.1 │
|
|
├───────────────────────────┼──────────┤
|
|
│ Recordings available: │ 13100 │
|
|
├───────────────────────────┼──────────┤
|
|
│ Features available: │ 13100 │
|
|
├───────────────────────────┼──────────┤
|
|
│ Supervisions available: │ 13100 │
|
|
╘═══════════════════════════╧══════════╛
|
|
"""
|