代码拉取完成，页面将自动刷新
同步操作将从 PaddlePaddle/PaddleSpeech 强制同步，此操作会覆盖自 Fork 仓库以来所做的任何修改，且无法恢复！！！
确定后同步将在后台操作，完成时将刷新页面，请耐心等待。
Download LJSpeech-1.1 from it's Official Website and extract it to ~/datasets. Then the dataset is in the directory ~/datasets/LJSpeech-1.1.
Assume the path to the dataset is ~/datasets/LJSpeech-1.1 and extract it to ~/datasets. Then the dataset is in the directory ~/datasets/LJSpeech-1.1.
Run the command below to
metadata.jsonl../run.sh
You can choose a range of stages you want to run, or set stage equal to stop-stage to use only one stage, for example, running the following command will only preprocess the dataset.
./run.sh --stage 0 --stop-stage 0
./local/preprocess.sh ${conf_path}
When it is done. A dump folder is created in the current directory. The structure of the dump folder is listed below.
dump
├── dev
│ ├── norm
│ └── raw
├── phone_id_map.txt
├── speaker_id_map.txt
├── test
│ ├── norm
│ └── raw
└── train
├── norm
├── raw
└── speech_stats.npy
The dataset is split into 3 parts, namely train, dev, and test, each of which contains a norm and raw subfolder. The raw folder contains the speech feature of each utterance, while the norm folder contains normalized ones. The statistics used to normalize features are computed from the training set, which is located in dump/train/speech_stats.npy.
Also, there is a metadata.jsonl in each subfolder. It is a table-like file that contains phones, text_lengths, speech_lengths, the path of speech features, speaker, and id of each utterance.
./local/train.sh calls ${BIN_DIR}/train.py.
CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${train_output_path}
Here's the complete help message.
usage: train.py [-h] [--config CONFIG] [--train-metadata TRAIN_METADATA]
[--dev-metadata DEV_METADATA] [--output-dir OUTPUT_DIR]
[--ngpu NGPU] [--phones-dict PHONES_DICT]
Train a TransformerTTS model with LJSpeech TTS dataset.
optional arguments:
-h, --help show this help message and exit
--config CONFIG TransformerTTS config file.
--train-metadata TRAIN_METADATA
training data.
--dev-metadata DEV_METADATA
dev data.
--output-dir OUTPUT_DIR
output dir.
--ngpu NGPU if ngpu == 0, use cpu.
--phones-dict PHONES_DICT
phone vocabulary file.
--config is a config file in yaml format to overwrite the default config, which can be found at conf/default.yaml.--train-metadata and --dev-metadata should be the metadata file in the normalized subfolder of train and dev in the dump folder.--output-dir is the directory to save the results of the experiment. Checkpoints are saved in checkpoints/ inside this directory.--ngpu is the number of gpus to use, if ngpu == 0, use cpu.--phones-dict is the path of the phone vocabulary file.We use waveflow as the neural vocoder. Download Pretrained WaveFlow Model with residual channel equals 128 from waveflow_ljspeech_ckpt_0.3.zip and unzip it.
unzip waveflow_ljspeech_ckpt_0.3.zip
WaveFlow checkpoint contains files listed below.
waveflow_ljspeech_ckpt_0.3
├── config.yaml # default config used to train waveflow
└── step-2000000.pdparams # model parameters of waveflow
./local/synthesize.sh calls ${BIN_DIR}/synthesize.py, which can synthesize waveform from metadata.jsonl.
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
usage: synthesize.py [-h] [--transformer-tts-config TRANSFORMER_TTS_CONFIG]
[--transformer-tts-checkpoint TRANSFORMER_TTS_CHECKPOINT]
[--transformer-tts-stat TRANSFORMER_TTS_STAT]
[--waveflow-config WAVEFLOW_CONFIG]
[--waveflow-checkpoint WAVEFLOW_CHECKPOINT]
[--phones-dict PHONES_DICT]
[--test-metadata TEST_METADATA] [--output-dir OUTPUT_DIR]
[--ngpu NGPU]
Synthesize with transformer tts & waveflow.
optional arguments:
-h, --help show this help message and exit
--transformer-tts-config TRANSFORMER_TTS_CONFIG
transformer tts config file.
--transformer-tts-checkpoint TRANSFORMER_TTS_CHECKPOINT
transformer tts checkpoint to load.
--transformer-tts-stat TRANSFORMER_TTS_STAT
mean and standard deviation used to normalize
spectrogram when training transformer tts.
--waveflow-config WAVEFLOW_CONFIG
waveflow config file.
--waveflow-checkpoint WAVEFLOW_CHECKPOINT
waveflow checkpoint to load.
--phones-dict PHONES_DICT
phone vocabulary file.
--test-metadata TEST_METADATA
test metadata.
--output-dir OUTPUT_DIR
output dir.
--ngpu NGPU if ngpu == 0, use cpu.
./local/synthesize_e2e.sh calls ${BIN_DIR}/synthesize_e2e.py, which can synthesize waveform from text file.
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name}
usage: synthesize_e2e.py [-h]
[--transformer-tts-config TRANSFORMER_TTS_CONFIG]
[--transformer-tts-checkpoint TRANSFORMER_TTS_CHECKPOINT]
[--transformer-tts-stat TRANSFORMER_TTS_STAT]
[--waveflow-config WAVEFLOW_CONFIG]
[--waveflow-checkpoint WAVEFLOW_CHECKPOINT]
[--phones-dict PHONES_DICT] [--text TEXT]
[--output-dir OUTPUT_DIR] [--ngpu NGPU]
Synthesize with transformer tts & waveflow.
optional arguments:
-h, --help show this help message and exit
--transformer-tts-config TRANSFORMER_TTS_CONFIG
transformer tts config file.
--transformer-tts-checkpoint TRANSFORMER_TTS_CHECKPOINT
transformer tts checkpoint to load.
--transformer-tts-stat TRANSFORMER_TTS_STAT
mean and standard deviation used to normalize
spectrogram when training transformer tts.
--waveflow-config WAVEFLOW_CONFIG
waveflow config file.
--waveflow-checkpoint WAVEFLOW_CHECKPOINT
waveflow checkpoint to load.
--phones-dict PHONES_DICT
phone vocabulary file.
--text TEXT text to synthesize, a 'utt_id sentence' pair per line.
--output-dir OUTPUT_DIR
output dir.
--ngpu NGPU if ngpu == 0, use cpu.
--transformer-tts-config, --transformer-tts-checkpoint, --transformer-tts-stat and --phones-dict are arguments for transformer_tts, which correspond to the 4 files in the transformer_tts pretrained model.--waveflow-config, --waveflow-checkpoint are arguments for waveflow, which correspond to the 2 files in the waveflow pretrained model.--test-metadata should be the metadata file in the normalized subfolder of test in the dump folder.--text is the text file, which contains sentences to synthesize.--output-dir is the directory to save synthesized audio files.--ngpu is the number of gpus to use, if ngpu == 0, use cpu.Pretrained Model can be downloaded here:
TransformerTTS checkpoint contains files listed below.
transformer_tts_ljspeech_ckpt_0.4
├── default.yaml # default config used to train transformer_tts
├── phone_id_map.txt # phone vocabulary file when training transformer_tts
├── snapshot_iter_201500.pdz # model parameters and optimizer states
└── speech_stats.npy # statistics used to normalize spectrogram when training transformer_tts
You can use the following scripts to synthesize for ${BIN_DIR}/../sentences_en.txt using pretrained transformer_tts and waveflow models.
source path.sh
FLAGS_allocator_strategy=naive_best_fit \
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
python3 ${BIN_DIR}/synthesize_e2e.py \
--transformer-tts-config=transformer_tts_ljspeech_ckpt_0.4/default.yaml \
--transformer-tts-checkpoint=transformer_tts_ljspeech_ckpt_0.4/snapshot_iter_201500.pdz \
--transformer-tts-stat=transformer_tts_ljspeech_ckpt_0.4/speech_stats.npy \
--waveflow-config=waveflow_ljspeech_ckpt_0.3/config.yaml \
--waveflow-checkpoint=waveflow_ljspeech_ckpt_0.3/step-2000000.pdparams \
--text=${BIN_DIR}/../sentences_en.txt \
--output-dir=exp/default/test_e2e \
--phones-dict=transformer_tts_ljspeech_ckpt_0.4/phone_id_map.txt
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。
马建仓 AI 助手