ttslearn.dnntts¶
DNN音声合成のためのモジュールです。
TTS¶
The TTS functionality is accessible from ttslearn.dnntts.*
-
class
ttslearn.dnntts.tts.
DNNTTS
(model_dir=None, device='cpu')[source]¶ DNN-based text-to-speech
- Parameters
Examples:
from ttslearn.dnntts import DNNTTS import matplotlib.pyplot as plt engine = DNNTTS() wav, sr = engine.tts("日本語音声合成のデモです。") fig, ax = plt.subplots(figsize=(8,2)) librosa.display.waveplot(wav.astype(np.float32), sr, ax=ax)
Models¶
The following models are acceible from ttslearn.dnntts.*
Feed-forward DNN¶
Multi-stream functionality¶
Split streams from multi-stream features |
|
Split streams and do apply MLPG if stream has dynamic features |
|
Get windows for parameter generation |
|
Get static sizes for each feature stream |
|
Get static features from static+dynamic features |
Generation utility¶
Predict phoneme durations. |
|
Predict acoustic features. |
|
Generate waveform from acoustic features. |