Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,390 Bytes
45ee559 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
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.delightful_tts_config import DelightfulTtsAudioConfig, DelightfulTTSConfig
from TTS.tts.models.delightful_tts import DelightfulTtsArgs, VocoderConfig
config_path = os.path.join(get_tests_output_path(), "test_model_config.json")
output_path = os.path.join(get_tests_output_path(), "train_outputs")
audio_config = DelightfulTtsAudioConfig()
model_args = DelightfulTtsArgs(use_speaker_embedding=False)
vocoder_config = VocoderConfig()
config = DelightfulTTSConfig(
model_args=model_args,
audio=audio_config,
vocoder=vocoder_config,
batch_size=2,
eval_batch_size=8,
compute_f0=True,
run_eval=True,
test_delay_epochs=-1,
text_cleaner="english_cleaners",
use_phonemes=True,
phoneme_language="en-us",
phoneme_cache_path="tests/data/ljspeech/phoneme_cache/",
f0_cache_path="tests/data/ljspeech/f0_cache_delightful/", ## delightful f0 cache is incompatible with other models
epochs=1,
print_step=1,
print_eval=True,
binary_align_loss_alpha=0.0,
use_attn_priors=False,
test_sentences=[
["Be a voice, not an echo.", "ljspeech"],
],
output_path=output_path,
num_speakers=4,
use_speaker_embedding=True,
)
# active multispeaker d-vec mode
config.model_args.use_speaker_embedding = True
config.model_args.use_d_vector_file = False
config.model_args.d_vector_file = None
config.model_args.d_vector_dim = 256
config.save_json(config_path)
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 "
"--coqpit.datasets.0.dataset_name ljspeech "
"--coqpit.datasets.0.meta_file_train metadata.csv "
"--coqpit.datasets.0.meta_file_val metadata.csv "
"--coqpit.datasets.0.path tests/data/ljspeech "
"--coqpit.datasets.0.meta_file_attn_mask tests/data/ljspeech/metadata_attn_mask.txt "
"--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"
# 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} --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)
shutil.rmtree("tests/data/ljspeech/f0_cache_delightful/")
|