mirror of https://github.com/coqui-ai/TTS.git
add wavernn tests + name refactoring
This commit is contained in:
sanjaesc
erogol
parent
016a77fcf2
commit
ea9d8755de
|
|
@ -0,0 +1,94 @@
|
|||
{
|
||||
"run_name": "wavernn_test",
|
||||
"run_description": "wavernn_test training",
|
||||
|
||||
// AUDIO PARAMETERS
|
||||
"audio":{
|
||||
"fft_size": 1024, // number of stft frequency levels. Size of the linear spectogram frame.
|
||||
"win_length": 1024, // stft window length in ms.
|
||||
"hop_length": 256, // stft window hop-lengh in ms.
|
||||
"frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
|
||||
"frame_shift_ms": null, // stft window hop-lengh in ms. If null, 'hop_length' is used.
|
||||
|
||||
// Audio processing parameters
|
||||
"sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
|
||||
"preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
|
||||
"ref_level_db": 0, // reference level db, theoretically 20db is the sound of air.
|
||||
|
||||
// Silence trimming
|
||||
"do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
|
||||
"trim_db": 60, // threshold for timming silence. Set this according to your dataset.
|
||||
|
||||
// MelSpectrogram parameters
|
||||
"num_mels": 80, // size of the mel spec frame.
|
||||
"mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
|
||||
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
|
||||
"spec_gain": 20.0, // scaler value appplied after log transform of spectrogram.
|
||||
|
||||
// Normalization parameters
|
||||
"signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
|
||||
"min_level_db": -100, // lower bound for normalization
|
||||
"symmetric_norm": true, // move normalization to range [-1, 1]
|
||||
"max_norm": 4.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
|
||||
"clip_norm": true, // clip normalized values into the range.
|
||||
"stats_path": null // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// Generating / Synthesizing
|
||||
"batched": true,
|
||||
"target_samples": 11000, // target number of samples to be generated in each batch entry
|
||||
"overlap_samples": 550, // number of samples for crossfading between batches
|
||||
|
||||
// DISTRIBUTED TRAINING
|
||||
// "distributed":{
|
||||
// "backend": "nccl",
|
||||
// "url": "tcp:\/\/localhost:54321"
|
||||
// },
|
||||
|
||||
// MODEL PARAMETERS
|
||||
"use_aux_net": true,
|
||||
"use_upsample_net": true,
|
||||
"upsample_factors": [4, 8, 8], // this needs to correctly factorise hop_length
|
||||
"seq_len": 1280, // has to be devideable by hop_length
|
||||
"mode": "mold", // mold [string], gauss [string], bits [int]
|
||||
"mulaw": false, // apply mulaw if mode is bits
|
||||
"padding": 2, // pad the input for resnet to see wider input length
|
||||
|
||||
// DATASET
|
||||
//"use_gta": true, // use computed gta features from the tts model
|
||||
"data_path": "tests/data/ljspeech/wavs/", // path containing training wav files
|
||||
"feature_path": null, // path containing computed features from wav files if null compute them
|
||||
|
||||
// TRAINING
|
||||
"batch_size": 4, // Batch size for training. Lower values than 32 might cause hard to learn attention.
|
||||
"epochs": 1, // total number of epochs to train.
|
||||
|
||||
// VALIDATION
|
||||
"run_eval": true,
|
||||
"test_every_epochs": 10, // Test after set number of epochs (Test every 20 epochs for example)
|
||||
|
||||
// OPTIMIZER
|
||||
"grad_clip": 4, // apply gradient clipping if > 0
|
||||
"lr_scheduler": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_params": {
|
||||
"gamma": 0.5,
|
||||
"milestones": [200000, 400000, 600000]
|
||||
},
|
||||
"lr": 1e-4, // initial learning rate
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 25, // Number of steps to log traning on console.
|
||||
"print_eval": false, // If True, it prints loss values for each step in eval run.
|
||||
"save_step": 25000, // Number of training steps expected to plot training stats on TB and save model checkpoints.
|
||||
"checkpoint": true, // If true, it saves checkpoints per "save_step"
|
||||
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
|
||||
|
||||
// DATA LOADING
|
||||
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 10, // number of samples for testing
|
||||
|
||||
// PATHS
|
||||
"output_path": "tests/train_outputs/"
|
||||
}
|
||||
|
||||
|
|
@ -5,11 +5,11 @@ echo "$BASEDIR"
|
|||
# create run dir
|
||||
mkdir $BASEDIR/train_outputs
|
||||
# run training
|
||||
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json
|
||||
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_gan_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_multiband_melgan_config.json
|
||||
# find the training folder
|
||||
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
|
||||
echo $LATEST_FOLDER
|
||||
# continue the previous training
|
||||
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_vocoder.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
|
||||
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_gan_vocoder.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
|
||||
# remove all the outputs
|
||||
rm -rf $BASEDIR/train_outputs/$LATEST_FOLDER
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
import numpy as np
|
||||
import torch
|
||||
import random
|
||||
from TTS.vocoder.models.wavernn import WaveRNN
|
||||
|
||||
|
||||
def test_wavernn():
|
||||
model = WaveRNN(
|
||||
rnn_dims=512,
|
||||
fc_dims=512,
|
||||
mode=10,
|
||||
mulaw=False,
|
||||
pad=2,
|
||||
use_aux_net=True,
|
||||
use_upsample_net=True,
|
||||
upsample_factors=[4, 8, 8],
|
||||
feat_dims=80,
|
||||
compute_dims=128,
|
||||
res_out_dims=128,
|
||||
res_blocks=10,
|
||||
hop_length=256,
|
||||
sample_rate=22050,
|
||||
)
|
||||
dummy_x = torch.rand((2, 1280))
|
||||
dummy_m = torch.rand((2, 80, 9))
|
||||
y_size = random.randrange(20, 60)
|
||||
dummy_y = torch.rand((80, y_size))
|
||||
output = model(dummy_x, dummy_m)
|
||||
assert np.all(output.shape == (2, 1280, 4 * 256)), output.shape
|
||||
output = model.generate(dummy_y, True, 5500, 550, False)
|
||||
assert np.all(output.shape == (256 * (y_size - 1),))
|
||||
|
|
@ -0,0 +1,91 @@
|
|||
import os
|
||||
import shutil
|
||||
|
||||
import numpy as np
|
||||
from tests import get_tests_path, get_tests_input_path, get_tests_output_path
|
||||
from torch.utils.data import DataLoader
|
||||
|
||||
from TTS.utils.audio import AudioProcessor
|
||||
from TTS.utils.io import load_config
|
||||
from TTS.vocoder.datasets.wavernn_dataset import WaveRNNDataset
|
||||
from TTS.vocoder.datasets.preprocess import load_wav_feat_data, preprocess_wav_files
|
||||
|
||||
file_path = os.path.dirname(os.path.realpath(__file__))
|
||||
OUTPATH = os.path.join(get_tests_output_path(), "loader_tests/")
|
||||
os.makedirs(OUTPATH, exist_ok=True)
|
||||
|
||||
C = load_config(os.path.join(get_tests_input_path(),
|
||||
"test_vocoder_wavernn_config.json"))
|
||||
|
||||
test_data_path = os.path.join(get_tests_path(), "data/ljspeech/")
|
||||
test_mel_feat_path = os.path.join(test_data_path, "mel")
|
||||
test_quant_feat_path = os.path.join(test_data_path, "quant")
|
||||
ok_ljspeech = os.path.exists(test_data_path)
|
||||
|
||||
|
||||
def wavernn_dataset_case(batch_size, seq_len, hop_len, pad, mode, num_workers):
|
||||
""" run dataloader with given parameters and check conditions """
|
||||
ap = AudioProcessor(**C.audio)
|
||||
|
||||
C.batch_size = batch_size
|
||||
C.mode = mode
|
||||
C.seq_len = seq_len
|
||||
C.data_path = test_data_path
|
||||
|
||||
preprocess_wav_files(test_data_path, C, ap)
|
||||
_, train_items = load_wav_feat_data(
|
||||
test_data_path, test_mel_feat_path, 5)
|
||||
|
||||
dataset = WaveRNNDataset(ap=ap,
|
||||
items=train_items,
|
||||
seq_len=seq_len,
|
||||
hop_len=hop_len,
|
||||
pad=pad,
|
||||
mode=mode,
|
||||
)
|
||||
# sampler = DistributedSampler(dataset) if num_gpus > 1 else None
|
||||
loader = DataLoader(dataset,
|
||||
shuffle=True,
|
||||
collate_fn=dataset.collate,
|
||||
batch_size=batch_size,
|
||||
num_workers=num_workers,
|
||||
pin_memory=True,
|
||||
)
|
||||
|
||||
max_iter = 10
|
||||
count_iter = 0
|
||||
|
||||
try:
|
||||
for data in loader:
|
||||
x_input, mels, _ = data
|
||||
expected_feat_shape = (ap.num_mels,
|
||||
(x_input.shape[-1] // hop_len) + (pad * 2))
|
||||
assert np.all(
|
||||
mels.shape[1:] == expected_feat_shape), f" [!] {mels.shape} vs {expected_feat_shape}"
|
||||
|
||||
assert (mels.shape[2] - pad * 2) * hop_len == x_input.shape[1]
|
||||
count_iter += 1
|
||||
if count_iter == max_iter:
|
||||
break
|
||||
# except AssertionError:
|
||||
# shutil.rmtree(test_mel_feat_path)
|
||||
# shutil.rmtree(test_quant_feat_path)
|
||||
finally:
|
||||
shutil.rmtree(test_mel_feat_path)
|
||||
shutil.rmtree(test_quant_feat_path)
|
||||
|
||||
|
||||
def test_parametrized_wavernn_dataset():
|
||||
''' test dataloader with different parameters '''
|
||||
params = [
|
||||
[16, C.audio['hop_length'] * 10, C.audio['hop_length'], 2, 10, 0],
|
||||
[16, C.audio['hop_length'] * 10, C.audio['hop_length'], 2, "mold", 4],
|
||||
[1, C.audio['hop_length'] * 10, C.audio['hop_length'], 2, 9, 0],
|
||||
[1, C.audio['hop_length'], C.audio['hop_length'], 2, 10, 0],
|
||||
[1, C.audio['hop_length'], C.audio['hop_length'], 2, "mold", 0],
|
||||
[1, C.audio['hop_length'] * 5, C.audio['hop_length'], 4, 10, 2],
|
||||
[1, C.audio['hop_length'] * 5, C.audio['hop_length'], 2, "mold", 0],
|
||||
]
|
||||
for param in params:
|
||||
print(param)
|
||||
wavernn_dataset_case(*param)
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
BASEDIR=$(dirname "$0")
|
||||
echo "$BASEDIR"
|
||||
# create run dir
|
||||
mkdir $BASEDIR/train_outputs
|
||||
# run training
|
||||
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_wavernn_vocoder.py --config_path $BASEDIR/inputs/test_vocoder_wavernn_config.json
|
||||
# find the training folder
|
||||
LATEST_FOLDER=$(ls $BASEDIR/train_outputs/| sort | tail -1)
|
||||
echo $LATEST_FOLDER
|
||||
# continue the previous training
|
||||
CUDA_VISIBLE_DEVICES="" python TTS/bin/train_wavernn_vocoder.py --continue_path $BASEDIR/train_outputs/$LATEST_FOLDER
|
||||
# remove all the outputs
|
||||
rm -rf $BASEDIR/train_outputs/$LATEST_FOLDER
|
||||
Loading…
Reference in New Issue