mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-08 16:44:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

minor updates

Browse Source
This commit is contained in:
JinZr 2023-08-25 19:30:05 +08:00
parent 3672d23631
commit d335152fd2
2 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
egs/swbd/ASR/README.md
View File

@ -27,6 +27,6 @@ See [RESULTS](/egs/swbd/ASR/RESULTS.md) for details.
The training script for `conformer_ctc` comes from the LibriSpeech `conformer_ctc` recipe in icefall.
A lot of the scripts for data processing are from the first-gen Kaldi and the ESPNet project, tailored to incorporate with Lhotse and icefall.
A lot of the scripts for data processing are from the first-gen Kaldi and the ESPNet project, tailored by myself to incorporate with Lhotse and Icefall.
Some of the scripts for text normalization are from stale pull requests of [Piotr Żelasko](https://github.com/pzelasko) and [Nagendra Goel](https://github.com/ngoel17).

32
egs/swbd/ASR/local/display_manifest_statistics.py
View File

@ -84,41 +84,41 @@ Speech duration statistics:
Eval2000 Cut statistics:
╒═══════════════════════════╤══════════╕
│ Cuts count: │ 2709 │
│ Cuts count: │ 4473 │
├───────────────────────────┼──────────┤
│ Total duration (hh:mm:ss) │ 01:39:19 │
│ Total duration (hh:mm:ss) │ 03:37:13 │
├───────────────────────────┼──────────┤
│ mean │ 2.2 │
│ mean │ 2.9 │
├───────────────────────────┼──────────┤
│ std │ 1.8 │
│ std │ 2.6 │
├───────────────────────────┼──────────┤
│ min │ 0.1 │
├───────────────────────────┼──────────┤
│ 25% │ 0.7 │
│ 25% │ 1.2 │
├───────────────────────────┼──────────┤
│ 50% │ 1.7 │
│ 50% │ 2.1 │
├───────────────────────────┼──────────┤
│ 75% │ 3.1 │
│ 75% │ 4.0 │
├───────────────────────────┼──────────┤
│ 99% │ 8.0 │
│ 99% │ 12.6 │
├───────────────────────────┼──────────┤
│ 99.5% │ 8.3 │
│ 99.5% │ 13.7 │
├───────────────────────────┼──────────┤
│ 99.9% │ 11.3 │
│ 99.9% │ 14.7 │
├───────────────────────────┼──────────┤
│ max │ 14.1 │
│ max │ 15.5 │
├───────────────────────────┼──────────┤
│ Recordings available: │ 2709 │
│ Recordings available: │ 4473 │
├───────────────────────────┼──────────┤
│ Features available: │ 0 │
│ Features available: │ 4473 │
├───────────────────────────┼──────────┤
│ Supervisions available: │ 2709 │
│ Supervisions available: │ 4473 │
╘═══════════════════════════╧══════════╛
Speech duration statistics:
╒══════════════════════════════╤══════════╤══════════════════════╕
│ Total speech duration │ 01:39:19 │ 100.00% of recording │
│ Total speech duration │ 03:37:13 │ 100.00% of recording │
├──────────────────────────────┼──────────┼──────────────────────┤
│ Total speaking time duration │ 01:39:19 │ 100.00% of recording │
│ Total speaking time duration │ 03:37:13 │ 100.00% of recording │
├──────────────────────────────┼──────────┼──────────────────────┤
│ Total silence duration │ 00:00:00 │ 0.00% of recording │
╘══════════════════════════════╧══════════╧══════════════════════╛