Skip to content

Commit fd1838b

Browse files
committed
Fix readme's to have information about language
1 parent 2afea67 commit fd1838b

File tree

2 files changed

+10
-8
lines changed

2 files changed

+10
-8
lines changed

examples/fastspeech2_multispeaker/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Fast speech 2 multi-speaker
1+
# Fast speech 2 multi-speaker english lang based
22

33
## Prepare
44
Everything is done from main repo folder so TensorflowTTS/

examples/mfa_extraction/README.md

Lines changed: 9 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,20 +1,22 @@
1-
# MFA based extraction for Fast speech
1+
# MFA based extraction for Fast speech
22

33
## Prepare
44
Everything is done from main repo folder so TensorflowTTS/
55

6-
* bash examples/mfa_extraction/scripts/prepare_mfa.sh
7-
* python examples/mfa_extraction/run_mfa.py --corpus_directory=< your dataset path >
6+
0. Optional* Modify MFA scripts to work with your language
7+
8+
1. bash examples/mfa_extraction/scripts/prepare_mfa.sh
9+
python examples/mfa_extraction/run_mfa.py --corpus_directory=< your dataset path >
810

911
(corpus_directory should be splited based on speakers example => dataset/speaker_1/001.wav dataset/speaker_1/001.txt)
1012

11-
* python examples/mfa_extraction/txt_grid_parser.py
13+
2. python examples/mfa_extraction/txt_grid_parser.py
1214

13-
* Optional* add your own dataset parser based on tensorflow_tts/processor/experiment/example_dataset.py ( If base processor dataset didnt match yours )
15+
3. Optional* add your own dataset parser based on tensorflow_tts/processor/experiment/example_dataset.py ( If base processor dataset didnt match yours )
1416

15-
* Run preprocess and normalization using preprocess_multispeaker.yaml or preprocess_libritts.yaml based config
17+
4. Run preprocess and normalization using preprocess_multispeaker.yaml or preprocess_libritts.yaml based config
1618

17-
* Run fix mismatch to fix few frames difference in audio and duration files examples/mfa_extraction/fix_mismatch.py --base_path=< your preprocess outdir location on above step >
19+
5. Run fix mismatch to fix few frames difference in audio and duration files examples/mfa_extraction/fix_mismatch.py --base_path=< your preprocess outdir location on above step >
1820
--trimmed_dur_path=< trimmed durations directory > --dur_path=< durations directory >
1921

2022

0 commit comments

Comments
 (0)