Malay Text-to-Speech Voice Model for Yasmin

Azure Tts Yasmin is a text-to-speech voice model for the Malay language, created by mesolitica and uploaded to Hugging Face in August 2022. The model is associated with the 'Regionus' tag, suggesting a regional focus. Specific details on dataset size, audio samples, or training methodology are not provided in the available metadata.

Use Cases

• Synthesizing Malay speech from text input using the 'Yasmin' voice profile.
• Fine-tuning or benchmarking TTS models for the Malay language.
• Studying acoustic features and prosody in synthesized Malay speech.

Strengths

• Model was uploaded to a major platform (Hugging Face) in 2022, indicating a degree of accessibility.
• Focuses on the Malay language, which is a less common target for TTS resources.

Limitations

• No dataset details (rows, size, audio specifications) are available for evaluation.
• The model's performance, audio quality, and training data provenance are unknown.
• Last update was in 2022, which may indicate staleness compared to current TTS advancements.

Provenance

Source

Uploaded by author 'mesolitica' to Hugging Face.

Collection Method

Inferred to be a trained TTS model; specific data collection and training methods are unknown.

Freshness

Last updated on 2022-08-22.

Geography

Inferred focus on Malay language regions.