TTS/tests/tts_tests/test_tacotron2_d-vectors_train.py

import glob
import json
import os
import shutil

from trainer import get_last_checkpoint

from tests import get_device_id, get_tests_output_path, run_cli
from TTS.tts.configs.tacotron2_config import Tacotron2Config

config_path = os.path.join(get_tests_output_path(), "test_model_config.json")
output_path = os.path.join(get_tests_output_path(), "train_outputs")

config = Tacotron2Config(
    r=5,
    batch_size=8,
    eval_batch_size=8,
    num_loader_workers=0,
    num_eval_loader_workers=0,
    text_cleaner="english_cleaners",
    use_phonemes=False,
    phoneme_language="en-us",
    phoneme_cache_path=os.path.join(get_tests_output_path(), "train_outputs/phoneme_cache/"),
    run_eval=True,
    test_delay_epochs=-1,
    epochs=1,
    print_step=1,
    print_eval=True,
    use_speaker_embedding=False,
    use_d_vector_file=True,
    test_sentences=[
        "Be a voice, not an echo.",
    ],
    d_vector_file="tests/data/ljspeech/speakers.json",
    d_vector_dim=256,
    max_decoder_steps=50,
)

config.audio.do_trim_silence = True
config.audio.trim_db = 60
config.save_json(config_path)

# train the model for one epoch
command_train = (
    f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_tts.py --config_path {config_path} "
    f"--coqpit.output_path {output_path} "
    "--coqpit.datasets.0.formatter ljspeech_test "
    "--coqpit.datasets.0.meta_file_train metadata.csv "
    "--coqpit.datasets.0.meta_file_val metadata.csv "
    "--coqpit.datasets.0.path tests/data/ljspeech "
    "--coqpit.test_delay_epochs 0 "
)
run_cli(command_train)

# Find latest folder
continue_path = max(glob.glob(os.path.join(output_path, "*/")), key=os.path.getmtime)

# Inference using TTS API
continue_config_path = os.path.join(continue_path, "config.json")
continue_restore_path, _ = get_last_checkpoint(continue_path)
out_wav_path = os.path.join(get_tests_output_path(), "output.wav")
speaker_id = "ljspeech-1"
continue_speakers_path = config.d_vector_file

# Check integrity of the config
with open(continue_config_path, "r", encoding="utf-8") as f:
    config_loaded = json.load(f)
assert config_loaded["characters"] is not None
assert config_loaded["output_path"] in continue_path
assert config_loaded["test_delay_epochs"] == 0

# Load the model and run inference
inference_command = f"CUDA_VISIBLE_DEVICES='{get_device_id()}' tts --text 'This is an example.' --speaker_idx {speaker_id} --speakers_file_path {continue_speakers_path} --config_path {continue_config_path} --model_path {continue_restore_path} --out_path {out_wav_path}"
run_cli(inference_command)

# restore the model and continue training for one more epoch
command_train = f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_tts.py --continue_path {continue_path} "
run_cli(command_train)
shutil.rmtree(continue_path)