---
license: bsd
---

# Model Card for FALCO-TTS

<!-- Provide a quick summary of what the model is/does. -->

This model implements a three-stage, SPEAR-TTS-like model, supporting zero-shot and cross-language speech synthesis. </p>

We trained this model on the corpus MLS (https://openslr.org/94/) and WenetSpeech (https://openslr.org/121/), utilizing about 20,000 hours data, including English and Mandarin part. </p>

This model have the auto code-switch capability.

## Model Details

|Model                            |Parameters   |Attention     |Output Vocab size
|:---                             |:----        |:---          |:---
|text_to_semantic                 |240 M     |Causal        |1024
|semantic_to_coarse_acoustic      |370 M     |Causal        |1x 1,024
|coarse_acoustic_to_fine_acoustic |370 M     |No Causal     |7x 1,024