wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-11 12:00:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'reformat' into hifigan-reformat

Browse Source
This commit is contained in:
Eren Gölge
2021-04-12 12:00:17 +02:00
parent f519012dea 3c0d1d066d
commit a7f6045644
65 changed files with 315 additions and 311 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_aligntts_train.sh → tests/bash_tests/test_aligntts_train.sh
Regular → Executable
+4 -4
View File
@@ -3,11 +3,11 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_align_tts.py --config_path $BASEDIR/inputs/test_align_tts.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_align_tts.py --config_path $BASEDIR/../inputs/test_align_tts.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_align_tts.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_align_tts.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/
rm -rf $BASEDIR/../train_outputs/
tests/test_compute_statistics.sh → tests/bash_tests/test_compute_statistics.sh
+1 -1
View File
@@ -3,5 +3,5 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/compute_statistics.py --config_path $BASEDIR/inputs/test_glow_tts.json --out_path $BASEDIR/outputs/scale_stats.npy
CUDA_VISIBLE_DEVICES="" python TTS/bin/compute_statistics.py --config_path $BASEDIR/../inputs/test_glow_tts.json --out_path $BASEDIR/../outputs/scale_stats.npy
tests/test_demo_server.sh → tests/bash_tests/test_demo_server.sh
View File
tests/test_glow-tts_train.sh → tests/bash_tests/test_glow-tts_train.sh
+4 -4
View File
@@ -3,11 +3,11 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_glow_tts.py --config_path $BASEDIR/inputs/test_glow_tts.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_glow_tts.py --config_path $BASEDIR/../inputs/test_glow_tts.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_glow_tts.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_glow_tts.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/
rm -rf $BASEDIR/../train_outputs/
tests/test_resample.sh → tests/bash_tests/test_resample.sh
+1 -1
View File
@@ -4,7 +4,7 @@ BASEDIR=$(dirname "$0")
TARGET_SR=16000
echo "$BASEDIR"
#run the resample script
python TTS/bin/resample.py --input_dir $BASEDIR/data/ljspeech --output_dir $BASEDIR/outputs/resample_tests --output_sr $TARGET_SR
python TTS/bin/resample.py --input_dir $BASEDIR/../data/ljspeech --output_dir $BASEDIR/outputs/resample_tests --output_sr $TARGET_SR
#check samplerate of output
OUT_SR=$( (echo "import librosa" ; echo "y, sr = librosa.load('"$BASEDIR"/outputs/resample_tests/wavs/LJ001-0012.wav', sr=None)" ; echo "print(sr)") | python )
OUT_SR=$(($OUT_SR + 0))
tests/test_speedy_speech_train.sh → tests/bash_tests/test_speedy_speech_train.sh
+4 -4
View File
@@ -3,11 +3,11 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_speedy_speech.py --config_path $BASEDIR/inputs/test_speedy_speech.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_speedy_speech.py --config_path $BASEDIR/../inputs/test_speedy_speech.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_speedy_speech.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_speedy_speech.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/
rm -rf $BASEDIR/../train_outputs/
tests/test_tacotron_train.sh → tests/bash_tests/test_tacotron_train.sh
+12 -12
View File
@@ -4,33 +4,33 @@ BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --config_path $BASEDIR/inputs/test_tacotron_config.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --config_path $BASEDIR/../inputs/test_tacotron_config.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/
rm -rf $BASEDIR/../train_outputs/
# run Tacotron bi-directional decoder
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --config_path $BASEDIR/inputs/test_tacotron_bd_config.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --config_path $BASEDIR/../inputs/test_tacotron_bd_config.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/
rm -rf $BASEDIR/../train_outputs/
# Tacotron2
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --config_path $BASEDIR/inputs/test_tacotron2_config.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --config_path $BASEDIR/../inputs/test_tacotron2_config.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_tacotron.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/
rm -rf $BASEDIR/../train_outputs/
tests/test_vocoder_gan_train.sh → tests/bash_tests/test_vocoder_gan_train.sh
+5 -5
View File
@@ -3,13 +3,13 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# create run dir
mkdir $BASEDIR/train_outputs
mkdir $BASEDIR/../train_outputs
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_gan.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_gan.py --config_path $BASEDIR/../inputs/test_vocoder_multiband_melgan_config.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_gan.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_gan.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/$LATEST_FOLDER
rm -rf $BASEDIR/../train_outputs/$LATEST_FOLDER
tests/test_vocoder_wavegrad_train.sh → tests/bash_tests/test_vocoder_wavegrad_train.sh
+5 -5
View File
@@ -3,13 +3,13 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# create run dir
mkdir -p $BASEDIR/train_outputs
mkdir -p $BASEDIR/../train_outputs
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavegrad.py --config_path $BASEDIR/inputs/test_vocoder_wavegrad.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavegrad.py --config_path $BASEDIR/../inputs/test_vocoder_wavegrad.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavegrad.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavegrad.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/$LATEST_FOLDER
rm -rf $BASEDIR/../train_outputs/$LATEST_FOLDER
tests/test_vocoder_wavernn_train.sh → tests/bash_tests/test_vocoder_wavernn_train.sh
+5 -5
View File
@@ -3,13 +3,13 @@ set -xe
BASEDIR=$(dirname "$0")
echo "$BASEDIR"
# create run dir
mkdir -p $BASEDIR/train_outputs
mkdir -p $BASEDIR/../train_outputs
# run training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavernn.py --config_path $BASEDIR/inputs/test_vocoder_wavernn_config.json
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavernn.py --config_path $BASEDIR/../inputs/test_vocoder_wavernn_config.json
# find the training folder
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
LATEST_FOLDER=$(ls $BASEDIR/../train_outputs/| sort | tail -1)
echo $LATEST_FOLDER
# continue the previous training
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavernn.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder_wavernn.py --continue_path $BASEDIR/../train_outputs/$LATEST_FOLDER
# remove all the outputs
rm -rf $BASEDIR/train_outputs/$LATEST_FOLDER
rm -rf $BASEDIR/../train_outputs/$LATEST_FOLDER
tests/inputs/test_align_tts.json
+2 -2
View File
@@ -65,7 +65,7 @@
// MODEL PARAMETERS
"positional_encoding": true,
"hidden_channels": 256,
"hidden_channels_dp": 128,
"hidden_channels_dp": 256,
"encoder_type": "fftransformer",
"encoder_params":{
"hidden_channels_ffn": 1024 ,
@@ -87,7 +87,7 @@
"eval_batch_size":1,
"r": 1, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
"loss_masking": true, // enable / disable loss masking against the sequence padding.
"phase_start_steps": [0, 40000, 80000, 160000, 170000],
"phase_start_steps": null,
// LOSS PARAMETERS
tests/test_audio.py
+1 -1
View File
@@ -16,7 +16,7 @@ conf = load_config(os.path.join(get_tests_input_path(), "test_config.json"))
# pylint: disable=protected-access
class TestAudio(unittest.TestCase):
def __init__(self, *args, **kwargs):
super(TestAudio, self).__init__(*args, **kwargs)
super().__init__(*args, **kwargs)
self.ap = AudioProcessor(**conf.audio)
def test_audio_synthesis(self):
tests/test_loader.py
+1 -1
View File
@@ -28,7 +28,7 @@ print(" > Dynamic data loader test: {}".format(DATA_EXIST))
class TestTTSDataset(unittest.TestCase):
def __init__(self, *args, **kwargs):
super(TestTTSDataset, self).__init__(*args, **kwargs)
super().__init__(*args, **kwargs)
self.max_loader_iter = 4
self.ap = AudioProcessor(**c.audio)