Downloads · 30 days
36
47% of all-time downloads
traxlate-mms-tts-pol
payam1394/traxlate-mms-tts-pol
traxlate-mms-tts-pol is a text-to-speech model from payam1394. Use it when you need text read aloud. It is set up for transformers.js. The card lists the license as cc-by-nc-4.0.
facebook/mms-tts-pol (Meta MMS Polish VITS text-to-speech) converted to ONNX for transformers.js, laid out like the Xenova mms-tts- conversions (fp32 + q8 dynamic quantization). Converted with the transformers.js 3.8.…
All-time downloads
76
Public
Repo size
153 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx153 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers.js
- License
- cc-by-nc-4.0
- Model type
- vits
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026
- SHA
- ba59a2a4
Base models
Model card
From the Hugging Face model README
traxlate-mms-tts-pol
facebook/mms-tts-pol (Meta MMS
Polish VITS text-to-speech) converted to ONNX for
transformers.js, laid out
like the Xenova mms-tts-* conversions (fp32 + q8 dynamic quantization).
Converted with the transformers.js 3.8.1 conversion script (torch 2.6.0
legacy exporter, onnxslim skipped, fp16 omitted -- see quantize_config.json).
import { pipeline } from '@huggingface/transformers';
const synth = await pipeline('text-to-speech', 'payam1394/traxlate-mms-tts-pol', { dtype: 'q8' });
License: CC-BY-NC-4.0 (inherited from the MMS release).
- Task
- Text-to-Speech
- Library
- transformers.js
- Type
- vits
- License
- cc-by-nc-4.0
- Languages
- pl
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026