Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Active evaluation in speaker encoder test and use multispeaker dataset for this test

This commit is contained in:
Edresson Casanova 2022-03-07 19:25:04 -03:00
parent 3a7feadba4
commit 631aec6e88
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
tests/aux_tests/test_speaker_encoder_train.py
View File

@ -4,14 +4,14 @@ import shutil
from tests import get_device_id, get_tests_output_path, run_cli from tests import get_device_id, get_tests_output_path, run_cli
from TTS.config.shared_configs import BaseAudioConfig from TTS.config.shared_configs import BaseAudioConfig
from TTS.encoder.speaker_encoder_config import SpeakerEncoderConfig from TTS.encoder.configs.speaker_encoder_config import SpeakerEncoderConfig
def run_test_train(): def run_test_train():
command = ( command = (
f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_encoder.py --config_path {config_path} " f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_encoder.py --config_path {config_path} "
f"--coqpit.output_path {output_path} " f"--coqpit.output_path {output_path} "
"--coqpit.datasets.0.name ljspeech " "--coqpit.datasets.0.name ljspeech_test "
"--coqpit.datasets.0.meta_file_train metadata.csv " "--coqpit.datasets.0.meta_file_train metadata.csv "
"--coqpit.datasets.0.meta_file_val metadata.csv " "--coqpit.datasets.0.meta_file_val metadata.csv "
"--coqpit.datasets.0.path tests/data/ljspeech " "--coqpit.datasets.0.path tests/data/ljspeech "
@ -24,13 +24,16 @@ output_path = os.path.join(get_tests_output_path(), "train_outputs")
config = SpeakerEncoderConfig( config = SpeakerEncoderConfig(
batch_size=4, batch_size=4,
num_classes_in_batch=1, num_classes_in_batch=2,
num_utter_per_class=10, num_utter_per_class=2,
num_loader_workers=0, eval_num_classes_in_batch=2,
max_train_step=2, eval_num_utter_per_class=2,
num_loader_workers=1,
epochs=2,
print_step=1, print_step=1,
save_step=1, save_step=1,
print_eval=True, print_eval=True,
run_eval=True,
audio=BaseAudioConfig(num_mels=80), audio=BaseAudioConfig(num_mels=80),
) )
config.audio.do_trim_silence = True config.audio.do_trim_silence = True