wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-10 11:50:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

Doc update (#889)

Browse Source 
* Link source files from the docs

* Update glowTTS recipes for docs

* Add dataset downloaders
This commit is contained in:
Eren Gölge
2021-10-26 17:41:33 +02:00
committed by GitHub
parent 0cac3f330a
commit 035ed432bc
8 changed files with 295 additions and 266 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/conf.py
+11 -14
View File
@@ -39,20 +39,6 @@ master_doc = "index"
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
]
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
# This pattern also affects html_static_path and html_extra_path.
exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store', 'TODO/*']
source_suffix = [".rst", ".md"]
# extensions
extensions = [
'sphinx.ext.autodoc',
'sphinx.ext.autosummary',
@@ -68,6 +54,17 @@ extensions = [
"sphinx_inline_tabs",
]
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
# This pattern also affects html_static_path and html_extra_path.
exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store', 'TODO/*']
source_suffix = [".rst", ".md"]
myst_enable_extensions = ['linkify',]
# 'sphinxcontrib.katex',
docs/source/training_a_model.md
+4 -122
View File
@@ -15,62 +15,7 @@
`Nervous Beginners`.
A recipe for `GlowTTS` using `LJSpeech` dataset looks like below. Let's be creative and call this `train_glowtts.py`.
```python
# train_glowtts.py
import os
from TTS.trainer import Trainer, TrainingArgs
from TTS.tts.configs.shared_config import BaseDatasetConfig
from TTS.tts.configs.glow_tts_config import GlowTTSConfig
from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.glow_tts import GlowTTS
from TTS.utils.audio import AudioProcessor
output_path = os.path.dirname(os.path.abspath(__file__))
dataset_config = BaseDatasetConfig(
name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/")
)
config = GlowTTSConfig(
batch_size=32,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
text_cleaner="phoneme_cleaners",
use_phonemes=True,
phoneme_language="en-us",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
print_step=25,
print_eval=False,
mixed_precision=True,
output_path=output_path,
datasets=[dataset_config],
)
# init audio processor
ap = AudioProcessor(**config.audio.to_dict())
# load training samples
train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True)
# init model
model = GlowTTS(config)
# init the trainer and 🚀
trainer = Trainer(
TrainingArgs(),
config,
output_path,
model=model,
train_samples=train_samples,
eval_samples=eval_samples,
training_assets={"audio_processor": ap},
)
trainer.fit()
```{literalinclude} ../../recipes/ljspeech/glow_tts/train_glowtts.py
```
You need to change fields of the `BaseDatasetConfig` to match your dataset and then update `GlowTTSConfig`
@@ -162,7 +107,7 @@
$ tensorboard --logdir=<path to your training directory>
```
6. Monitor the training process.
6. Monitor the training progress.
On the terminal and Tensorboard, you can monitor the progress of your model. Also Tensorboard provides certain figures and sample outputs.
@@ -197,68 +142,5 @@ d-vectors. For using d-vectors, you first need to compute the d-vectors using th
The same Glow-TTS model above can be trained on a multi-speaker VCTK dataset with the script below.
```python
import os
from TTS.config.shared_configs import BaseAudioConfig
from TTS.trainer import Trainer, TrainingArgs
from TTS.tts import BaseDatasetConfig, GlowTTSConfig
from TTS.tts.datasets import load_tts_samples
from TTS.tts.glow_tts import GlowTTS
from TTS.tts.utils.speakers import SpeakerManager
from TTS.utils.audio import AudioProcessor
# define dataset config for VCTK
output_path = os.path.dirname(os.path.abspath(__file__))
dataset_config = BaseDatasetConfig(name="vctk", meta_file_train="", path=os.path.join(output_path, "../VCTK/"))
# init audio processing config
audio_config = BaseAudioConfig(sample_rate=22050, do_trim_silence=True, trim_db=23.0)
# init training config
config = GlowTTSConfig(
batch_size=64,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
text_cleaner="phoneme_cleaners",
use_phonemes=True,
phoneme_language="en-us",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
print_step=25,
print_eval=False,
mixed_precision=True,
output_path=output_path,
datasets=[dataset_config],
use_speaker_embedding=True,
)
# init audio processor
ap = AudioProcessor(**config.audio.to_dict())
# load training samples
train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True)
# ONLY FOR MULTI-SPEAKER: init speaker manager for multi-speaker training
speaker_manager = SpeakerManager()
speaker_manager.set_speaker_ids_from_data(train_samples + eval_samples)
config.num_speakers = speaker_manager.num_speakers
# init model
model = GlowTTS(config, speaker_manager)
# init the trainer and 🚀
trainer = Trainer(
TrainingArgs(),
config,
output_path,
model=model,
train_samples=train_samples,
eval_samples=eval_samples,
training_assets={"audio_processor": ap},
)
trainer.fit()
```
```{literalinclude} ../../recipes/vctk/glow_tts/train_glow_tts.py
```
docs/source/tutorial_for_nervous_beginners.md
+11 -121
View File
@@ -18,80 +18,21 @@ $ pip install -e .
## Training a `tts` Model
A breakdown of a simple script training a GlowTTS model on LJspeech dataset. See the comments for the explanation of
each line.
A breakdown of a simple script that trains a GlowTTS model on the LJspeech dataset. See the comments for more details.
### Pure Python Way
0. Download your dataset.
In this example, we download and use the LJSpeech dataset. Set the download directory based on your preferences.
```bash
$ python -c 'from TTS.utils.downloaders import download_ljspeech; download_ljspeech("../recipes/ljspeech/");'
```
1. Define `train.py`.
```python
import os
# GlowTTSConfig: all model related values for training, validating and testing.
from TTS.tts.configs.glow_tts_config import GlowTTSConfig
# BaseDatasetConfig: defines name, formatter and path of the dataset.
from TTS.tts.configs.shared_config import BaseDatasetConfig
# init_training: Initialize and setup the training environment.
# Trainer: Where the ✨️ happens.
# TrainingArgs: Defines the set of arguments of the Trainer.
from TTS.trainer import init_training, Trainer, TrainingArgs
# we use the same path as this script as our training folder.
output_path = os.path.dirname(os.path.abspath(__file__))
# set LJSpeech as our target dataset and define its path so that the Trainer knows what data formatter it needs.
dataset_config = BaseDatasetConfig(name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/"))
# Configure the model. Every config class inherits the BaseTTSConfig to have all the fields defined for the Trainer.
config = GlowTTSConfig(
batch_size=32,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
text_cleaner="english_cleaners",
use_phonemes=False,
phoneme_language="en-us",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
print_step=25,
print_eval=True,
mixed_precision=False,
output_path=output_path,
datasets=[dataset_config]
)
# initialize the audio processor used for feature extraction and audio I/O.
# It is mainly used by the dataloader and the training loggers.
ap = AudioProcessor(**config.audio.to_dict())
# load a list of training samples
# Each sample is a list of ```[text, audio_file_path, speaker_name]```
train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True)
# initialize the model
# Models only takes the config object as input.
model = GlowTTS(config)
# Initiate the Trainer.
# Trainer provides a generic API to train all the 🐸TTS models with all its perks like mixed-precision training,
# distributed training, etc.
trainer = Trainer(
TrainingArgs(),
config,
output_path,
model=model,
train_samples=train_samples,
eval_samples=eval_samples,
training_assets={"audio_processor": ap},
)
# And kick it 🚀
trainer.fit()
```{literalinclude} ../../recipes/ljspeech/glow_tts/train_glowtts.py
```
2. Run the script.
@@ -154,58 +95,7 @@ We still support running training from CLI like in the old days. The same traini
## Training a `vocoder` Model
```python
import os
from TTS.trainer import Trainer, TrainingArgs
from TTS.utils.audio import AudioProcessor
from TTS.vocoder.configs import HifiganConfig
from TTS.vocoder.datasets.preprocess import load_wav_data
from TTS.vocoder.models.gan import GAN
output_path = os.path.dirname(os.path.abspath(__file__))
config = HifiganConfig(
batch_size=32,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=5,
epochs=1000,
seq_len=8192,
pad_short=2000,
use_noise_augment=True,
eval_split_size=10,
print_step=25,
print_eval=False,
mixed_precision=False,
lr_gen=1e-4,
lr_disc=1e-4,
data_path=os.path.join(output_path, "../LJSpeech-1.1/wavs/"),
output_path=output_path,
)
# init audio processor
ap = AudioProcessor(**config.audio.to_dict())
# load training samples
eval_samples, train_samples = load_wav_data(config.data_path, config.eval_split_size)
# init model
model = GAN(config)
# init the trainer and 🚀
trainer = Trainer(
TrainingArgs(),
config,
output_path,
model=model,
train_samples=train_samples,
eval_samples=eval_samples,
training_assets={"audio_processor": ap},
)
trainer.fit()
```{literalinclude} ../../recipes/ljspeech/hifigan/train_hifigan.py
```
❗️ Note that you can also use ```train_vocoder.py``` as the ```tts``` models above.