Vietnamese Text-To-Speech Audio From Literary Works

35.9 hours of Vietnamese audio generated for text-to-speech applications. The text source is a collection of public domain novels and short stories by author Vu Trong Phung. The audio was synthesized using the Google Text-to-Speech offline engine on Android.

Use Cases

• Train a text-to-speech model on 35.9 hours of Vietnamese audio paired with literary text.
• Fine-tune a voice synthesis model using audio generated from the Google TTS engine.
• Analyze prosody and pronunciation patterns in Vietnamese speech derived from Vu Trong Phung's writings.

Strengths

• Substantial audio duration of 35.9 hours for model training.
• Text sourced from a specific, named literary author (Vu Trong Phung).
• Clear origin of audio generation via the Google Text-to-Speech offline engine.

Limitations

• Audio is synthetically generated, not recorded from human speakers.
• Text scope is limited to the works of a single author, which may not represent general Vietnamese.
• Dataset size and specific file formats are not detailed in the provided input.

Provenance

Source

Text from novels and short stories by Vu Trong Phung.

Collection Method

Audio generated by Google Text-to-Speech offline engine on Android.

Freshness

Last updated on 2022-05-06.