|
Download README.md from codebucketsolutions/bolo-mms-tts-maithili: direct link, hf CLI and curl.
- Browser
- Download file 1.86 kB
-
https://huggingface.co/codebucketsolutions/bolo-mms-tts-maithili/resolve/main/README.md
- Command line
-
hf download hf://codebucketsolutions/bolo-mms-tts-maithili/README.md
-
curl -L -o README.md https://huggingface.co/codebucketsolutions/bolo-mms-tts-maithili/resolve/main/README.md
1.86 kB
| license: cc-by-nc-4.0 | |
| language: | |
| - mai | |
| pipeline_tag: text-to-speech | |
| tags: | |
| - bolo | |
| - sherpa-onnx | |
| - onnx | |
| - text-to-speech | |
| - tts | |
| - vits | |
| # mms-tts-mai | |
| Maithili voice converted for [bolo](https://github.com/cb-Sigma/bolo), a speech server that runs without PyTorch (sherpa-onnx). | |
| ## Use it | |
| ```bash | |
| bolo pull mms-tts-mai | |
| ``` | |
| ## Licence | |
| Weights: **CC-BY-NC-4.0** - non-commercial use only. | |
| The full licence text is in `LICENSE`. | |
| ## Attribution and provenance | |
| ``` | |
| mms-tts-mai: Maithili voice from Meta's Massively Multilingual Speech (MMS) project | |
| Model: https://huggingface.co/facebook/mms-tts/tree/44cc7fb408064ef9ea6e7c59130d88cac1274671/models/mai | |
| Authors: Vineel Pratap, Andros Tjandra, Bowen Shi, et al. (Meta AI), "Scaling Speech Technology to | |
| 1,000+ Languages", 2023, https://arxiv.org/abs/2305.13516 | |
| Licence: Creative Commons Attribution-NonCommercial 4.0 International (CC-BY-NC-4.0), | |
| https://creativecommons.org/licenses/by-nc/4.0/ (full text in LICENSE). NON-COMMERCIAL USE ONLY. | |
| Changes: format conversion only (PyTorch checkpoint to ONNX with the original VITS inference code, | |
| mms-meta/MMS at revision 65d863f41196654aa8b8f3dc586474a4c8f30934), made with tools/voices/export_mms.py of the | |
| bolo project (https://github.com/cb-Sigma/bolo). The weights were not retrained or otherwise changed. | |
| Inference code: VITS, MIT licence, Copyright (c) 2021 Jaehyeon Kim. | |
| ``` | |
| Source: https://huggingface.co/facebook/mms-tts/tree/44cc7fb408064ef9ea6e7c59130d88cac1274671/models/mai | |
| This repository holds a format conversion only; the weights were not retrained. | |
| ## Measured by the bolo maintainers | |
| | | | | |
| | --- | --- | | |
| | round-trip WER (5 sentences) | 0.486 | | |
| | round-trip CER | 0.129 | | |
| | recogniser | indicconformer-mai-community | | |
| | real-time factor (2 threads, shared 4 vCPU) | 0.523 | | |
| | time to first audio (ms) | 1534 | | |
| | date | 2026-11-13 | | |