forked from kaldi-asr/kaldi
-
Notifications
You must be signed in to change notification settings - Fork 25
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #131 from dabraude/master
adds script for custom voices
- Loading branch information
Showing
68 changed files
with
5,842 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,23 @@ | ||
# you can change cmd.sh depending on what type of queue you are using. | ||
# If you have no queueing system and want to run on a local machine, you | ||
# can change all instances 'queue.pl' to run.pl (but be careful and run | ||
# commands one by one: most recipes will exhaust the memory on your | ||
# machine). queue.pl works with GridEngine (qsub). slurm.pl works | ||
# with slurm. Different queues are configured differently, with different | ||
# queue names and different ways of specifying things like memory; | ||
# to account for these differences you can create and edit the file | ||
# conf/queue.conf to match your queue's configuration. Search for | ||
# conf/queue.conf in http://kaldi-asr.org/doc/queue.html for more information, | ||
# or search for the string 'default_config' in utils/queue.pl or utils/slurm.pl. | ||
|
||
export train_cmd=run.pl | ||
export decode_cmd="run.pl --mem 2G" | ||
# the use of cuda_cmd is deprecated, used only in 'nnet1', | ||
export cuda_cmd="run.pl --gpu 1" | ||
|
||
if [[ "$(hostname -f)" == "*.fit.vutbr.cz" ]]; then | ||
queue_conf=$HOME/queue_conf/default.conf # see example /homes/kazi/iveselyk/queue_conf/default.conf, | ||
export train_cmd="queue.pl --config $queue_conf --mem 2G --matylda 0.2" | ||
export decode_cmd="queue.pl --config $queue_conf --mem 3G --matylda 0.1" | ||
export cuda_cmd="queue.pl --config $queue_conf --gpu 1 --mem 10G --tmp 40G" | ||
fi |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,5 @@ | ||
hid_layers=2 | ||
hid-dim=1000 | ||
splice_lr=0 | ||
apply_cmvn=true | ||
apply_glob_cmvn=true |
4 changes: 4 additions & 0 deletions
4
idlak-egs/tts_tangle_custom/s2/conf/3-layer-nn-2splice10.conf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
hid_layers=3 | ||
insplice_lr=10 | ||
splice_lr=10 | ||
apply_glob_cmvn=true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
hid_layers=3 | ||
insplice_lr=10 | ||
splice_lr=0 | ||
apply_glob_cmvn=true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,5 @@ | ||
hid_layers=3 | ||
insplice_lr=5 | ||
insplice_step=1 | ||
splice_lr=0 | ||
apply_glob_cmvn=true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
hid_layers=3 | ||
splice_lr=0 | ||
apply_glob_cmvn=true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
hid_layers=4 | ||
splice_lr=0 | ||
apply_cmvn=true | ||
apply_glob_cmvn=true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,5 @@ | ||
hid_layers=2 | ||
splice_lr=0 | ||
apply_glob_cmvn=true | ||
apply_cmvn=false | ||
apply_minmax=false |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,8 @@ | ||
--snip-edges=false | ||
--frame-shift=5 | ||
--sample-frequency=48000 | ||
--num-mel-bins=25 | ||
--scale-type=bark | ||
--use-hts-bands=true | ||
--peak-quality=0.4 | ||
--peak-width=0.1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,9 @@ | ||
--snip-edges=false | ||
--frame-shift=5 | ||
--sample-frequency=16000 | ||
--num-mel-bins=21 | ||
--use-hts-bands=true | ||
--peak-quality=0.4 | ||
--peak-width=0.1 | ||
|
||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
#beam=18.0 # beam for decoding. Was 13.0 in the scripts. | ||
#latbeam=10.0 # this has most effect on size of the lattices. | ||
parallel_opts= |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
hid_layers=3 | ||
insplice= | ||
splice=0 | ||
delta_opts="--delta-order=2" | ||
minmax_opts=true | ||
learn_rate=0.001 | ||
hid_dim=100 | ||
network_type=lstm | ||
momentum=0.8 | ||
proto_opts="--no-softmax --cell-dim=100 --proj-dim=50 --num-layers=2 --activation-final --activation-type=<Sigmoid>" | ||
train_tool=nnet-train-multistream-perutt-tgtmat | ||
train_tool_opts="--objective-function=mse --num-streams=10" | ||
scheduler_opts="--min-iters 15" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,22 @@ | ||
hid_layers=3 | ||
insplice=5 | ||
splice=0 | ||
delta_opts= | ||
#"--delta-order=2" | ||
#minmax_opts= | ||
|
||
#proto_opts="--no-softmax --activation-type=<Tanh>" | ||
#learn_rate=0.0001 | ||
|
||
# --activation-final=<Sigmoid> | ||
#proto_opts="--no-softmax --activation-type=<Sigmoid>" | ||
#learn_rate=0.00001 | ||
cmvn_opts="--norm-means=false --norm-vars=true" | ||
minmax_opts= | ||
global_cmvn= | ||
proto_opts="--no-softmax --activation-type=<Sigmoid>" | ||
learn_rate=0.000005 | ||
momentum=0.2 | ||
hid_dim=100 | ||
halving_factor=0.75 | ||
max_iters=50 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
# No non-default options for now. | ||
--frame-shift=5 | ||
--num-mel-bins=50 | ||
--use-energy=true |
13 changes: 13 additions & 0 deletions
13
idlak-egs/tts_tangle_custom/s2/conf/full-lstm-splice5.conf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
hid_layers=3 | ||
insplice= | ||
splice=0 | ||
delta_opts="--delta-order=2" | ||
minmax_opts=true | ||
learn_rate=0.0001 | ||
hid_dim=100 | ||
network_type=lstm | ||
momentum=0.8 | ||
proto_opts="--no-softmax --cell-dim=1000 --proj-dim=700 --num-layers=2 --activation-final --activation-type=<Sigmoid>" | ||
train_tool=nnet-train-multistream-perutt-tgtmat | ||
train_tool_opts="--objective-function=mse --num-streams=10" | ||
scheduler_opts="--min-iters 15" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,11 @@ | ||
hid_layers=3 | ||
insplice=5 | ||
splice=0 | ||
delta_opts="--delta-order=2" | ||
proto_opts="--activation-final=<Sigmoid> --no-softmax --activation-type=<Sigmoid>" | ||
learn_rate=0.02 | ||
minmax_opts=true | ||
momentum=0.2 | ||
hid_dim=700 | ||
halving_factor=0.75 | ||
max_iters=50 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
srate=48000 | ||
order=60 | ||
alpha=0.55 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
srate=16000 | ||
order=39 | ||
alpha=0.42 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
--use-energy=false | ||
--frame-shift=5 | ||
--snip-edges=false | ||
--sample-frequency=48000 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
--use-energy=false | ||
--frame-shift=5 | ||
--snip-edges=false |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
--snip-edges=false | ||
--frame-shift=5 | ||
--sample-frequency=48000 | ||
--frame-length=30 |
13 changes: 13 additions & 0 deletions
13
idlak-egs/tts_tangle_custom/s2/conf/pitch-lstm-splice5.conf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
hid_layers=3 | ||
insplice= | ||
splice=0 | ||
delta_opts="--delta-order=2" | ||
minmax_opts=true | ||
learn_rate=0.0005 | ||
hid_dim=100 | ||
network_type=lstm | ||
momentum=0.8 | ||
proto_opts="--no-softmax --cell-dim=100 --proj-dim=50 --num-layers=2 --activation-final --activation-type=<Sigmoid>" | ||
train_tool=nnet-train-multistream-perutt-tgtmat | ||
train_tool_opts="--objective-function=mse --num-streams=10" | ||
scheduler_opts="--min-iters 15" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,22 @@ | ||
hid_layers=3 | ||
insplice=0 | ||
splice=0 | ||
delta_opts="--delta-order=2" | ||
minmax_opts=true | ||
#cmvn_opts="--norm-means=true --norm-vars=true" | ||
proto_opts="--activation-final=<Sigmoid> --no-softmax --activation-type=<Sigmoid>" | ||
learn_rate=0.02 | ||
momentum=0.2 | ||
hid_dim=128 | ||
halving_factor=0.5 | ||
max_iters=50 | ||
|
||
#cmvn_opts="--norm-means=false --norm-vars=true" | ||
#minmax_opts= | ||
#global_cmvn=true | ||
#proto_opts="--no-softmax --activation-type=<Sigmoid>" | ||
#learn_rate=0.02 | ||
#momentum=0.2 | ||
#hid_dim=100 | ||
#halving_factor=0.75 | ||
#max_iters=50 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
--snip-edges=false | ||
--frame-shift=5 | ||
--sample-frequency=16000 | ||
--frame-length=30 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
splice=4 | ||
delta_order=2 | ||
apply_cmvn=true | ||
copy_feats=true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,81 @@ | ||
#!/usr/bin/perl -w | ||
# Copyright 2012 Johns Hopkins University (Author: Daniel Povey) | ||
# Apache 2.0. | ||
|
||
# This program is a bit like ./sym2int.pl in that it applies a map | ||
# to things in a file, but it's a bit more general in that it doesn't | ||
# assume the things being mapped to are single tokens, they could | ||
# be sequences of tokens. | ||
|
||
# This program takes two arguments, which may be files or "-" for the | ||
# standard input. Both files must have lines with one or more fields, | ||
# interpreted as a map from the first field (a string) to a list of strings. | ||
# if the first file has as one of its lines | ||
# A x y | ||
# and the second has the lines | ||
# x P | ||
# y Q R | ||
# then the output of this program will be | ||
# A P Q R | ||
# | ||
# Note that if x or y did not appear as the first field of file b, we would | ||
# print a warning and omit the whole line rather than map it to the empty | ||
# string. | ||
|
||
|
||
if (@ARGV > 0 && $ARGV[0] eq "-f") { | ||
shift @ARGV; | ||
$field_spec = shift @ARGV; | ||
if ($field_spec =~ m/^\d+$/) { | ||
$field_begin = $field_spec - 1; $field_end = $field_spec - 1; | ||
} | ||
if ($field_spec =~ m/^(\d*)[-:](\d*)/) { # accept e.g. 1:10 as a courtesty (properly, 1-10) | ||
if ($1 ne "") { | ||
$field_begin = $1 - 1; # Change to zero-based indexing. | ||
} | ||
if ($2 ne "") { | ||
$field_end = $2 - 1; # Change to zero-based indexing. | ||
} | ||
} | ||
if (!defined $field_begin && !defined $field_end) { | ||
die "Bad argument to -f option: $field_spec"; | ||
} | ||
} | ||
|
||
|
||
if(@ARGV != 1) { | ||
print STDERR "Usage: apply_map.pl [options] map <input >output\n" . | ||
"options: [-f <field-range> ]\n" . | ||
"note: <field-range> can look like 4-5, or 4-, or 5-, or 1.\n" . | ||
"e.g.: echo A B | apply_map.pl a.txt\n" . | ||
"where a.txt is:\n" . | ||
"A a1 a2\n" . | ||
"B b\n" . | ||
"will produce:\n" . | ||
"a1 a2 b\n"; | ||
exit(1); | ||
} | ||
|
||
($map) = @ARGV; | ||
open(M, "<$map") || die "Error opening map file $map: $!"; | ||
|
||
while (<M>) { | ||
@A = split(" ", $_); | ||
@A >= 1 || die "apply_map.pl: empty line."; | ||
$i = shift @A; | ||
$o = join(" ", @A); | ||
$map{$i} = $o; | ||
} | ||
|
||
while(<STDIN>) { | ||
@A = split(" ", $_); | ||
for ($x = 0; $x < @A; $x++) { | ||
if ( (!defined $field_begin || $x >= $field_begin) | ||
&& (!defined $field_end || $x <= $field_end)) { | ||
$a = $A[$x]; | ||
if (!defined $map{$a}) { die "compose_maps.pl: undefined key $a\n"; } | ||
$A[$x] = $map{$a}; | ||
} | ||
} | ||
print join(" ", @A) . "\n"; | ||
} |
Oops, something went wrong.