# Japanese TTS

A lightweight text-to-speech model optimized for Japanese, improving inference speed through layer pruning, supporting 14 voice tones

Parler-TTS Mini v1 is a lightweight text-to-speech model, while Retrieva-JP T5 Base Long is a Japanese text processing model. They are combined for Japanese text-to-speech tasks.

Parler-TTS Mini v1 is a small Japanese text-to-speech model that supports high-quality speech synthesis.

Japanese child voice text-to-speech model trained on the style_bert_vits2_jp_extra framework, free for commercial use

Kotoba-Speech v0.1 is a Japanese speech generation model based on a 1.2B parameter Transformer, supporting text-to-speech and one-shot voice cloning.

SpeechT5 model fine-tuned on JVS Japanese speech corpus, specialized for Japanese text-to-speech (TTS) tasks

This is a Japanese text-to-speech (TTS) model trained on the ESPnet2 framework, using the VITS architecture, completed by mio on the amadeus dataset.

This is a Japanese text-to-speech model trained using the ESPnet2 framework, utilizing the JSUT dataset to support high-quality speech synthesis.

This is a Japanese text-to-speech (TTS) model trained on the ESPnet framework, fine-tuned using the JVS dataset, supporting high-quality Japanese speech synthesis.