Downloads · 30 days
0
falco
kristonai/falco
falco is a machine learning model from kristonai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd.
This model implements a three-stage, SPEAR-TTS-like model, supporting zero-shot and cross-language speech synthesis. </p
Access
Public
Updated Sep 7, 2023
Repo size
13.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt10.8 GB · 98%
At a glance
- License
- bsd
- Access
- Public
- Created
- Aug 21, 2023
- Updated
- Sep 7, 2023
- SHA
- 53e59e51
Model card
From the Hugging Face model README
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_acoustic | 370 M | Causal | 8x 1,024 |
- License
- bsd
- Created
- Aug 21, 2023
- Updated
- Sep 7, 2023