|
|
--- |
|
|
license: other |
|
|
license_name: svector |
|
|
license_link: LICENSE |
|
|
pipeline_tag: automatic-speech-recognition |
|
|
tags: |
|
|
- SVECTOR |
|
|
language: |
|
|
- en |
|
|
- zh |
|
|
- de |
|
|
- es |
|
|
- ru |
|
|
- ko |
|
|
- fr |
|
|
- ja |
|
|
- pt |
|
|
- tr |
|
|
- pl |
|
|
- ca |
|
|
- nl |
|
|
- ar |
|
|
- sv |
|
|
- it |
|
|
- id |
|
|
- hi |
|
|
- fi |
|
|
- vi |
|
|
- he |
|
|
- uk |
|
|
- el |
|
|
- ms |
|
|
- cs |
|
|
- ro |
|
|
- da |
|
|
- hu |
|
|
- ta |
|
|
- 'no' |
|
|
- th |
|
|
- ur |
|
|
- hr |
|
|
- bg |
|
|
- lt |
|
|
- la |
|
|
- mi |
|
|
- ml |
|
|
- cy |
|
|
- sk |
|
|
- te |
|
|
- fa |
|
|
- lv |
|
|
- bn |
|
|
- sr |
|
|
- az |
|
|
- sl |
|
|
- kn |
|
|
- et |
|
|
- mk |
|
|
- br |
|
|
- eu |
|
|
- is |
|
|
- hy |
|
|
- ne |
|
|
- mn |
|
|
- bs |
|
|
- kk |
|
|
- sq |
|
|
- sw |
|
|
- gl |
|
|
- mr |
|
|
- pa |
|
|
- si |
|
|
- km |
|
|
- sn |
|
|
- yo |
|
|
- so |
|
|
- af |
|
|
- oc |
|
|
- ka |
|
|
- be |
|
|
- tg |
|
|
- sd |
|
|
- gu |
|
|
- am |
|
|
- yi |
|
|
- lo |
|
|
- uz |
|
|
- fo |
|
|
- ht |
|
|
- ps |
|
|
- tk |
|
|
- nn |
|
|
- mt |
|
|
- sa |
|
|
- tl |
|
|
- mg |
|
|
- as |
|
|
- tt |
|
|
- haw |
|
|
- ln |
|
|
- ha |
|
|
- ba |
|
|
- jw |
|
|
- su |
|
|
--- |
|
|
|
|
|
# SPTK-2 |
|
|
|
|
|
**SPTK-2** is an open multilingual automatic speech recognition (ASR) model developed by **SVECTOR**. |
|
|
It supports (after revised) 96 languages and offers improved accuracy, timestamp precision, and energy efficiency compared to previous models. |
|
|
|
|
|
๐ Read the paper: [SPTK: A Framework for Universal Multilingual ASR (2025)](https://huggingface.co/SVECTOR-CORPORATION/SPTK-2/SPTK.pdf) |
|
|
|
|
|
--- |
|
|
|
|
|
## ๐งช Example Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq |
|
|
import torchaudio |
|
|
|
|
|
processor = AutoProcessor.from_pretrained("SVECTOR-CORPORATION/SPTK-2") |
|
|
model = AutoModelForSpeechSeq2Seq.from_pretrained("SVECTOR-CORPORATION/SPTK-2") |
|
|
|
|
|
# Load and preprocess audio |
|
|
audio, sr = torchaudio.load("your_audio_file.mp3") |
|
|
inputs = processor(audio[0], sampling_rate=sr, return_tensors="pt") |
|
|
|
|
|
# Generate transcription |
|
|
with torch.no_grad(): |
|
|
predicted_ids = model.generate(inputs.input_values) |
|
|
|
|
|
# Decode output |
|
|
print(processor.batch_decode(predicted_ids, skip_special_tokens=True)) |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
## ๐ฆ Model Details |
|
|
|
|
|
- Model type: Encoder-decoder |
|
|
- Architecture: E-Branchformer + Sparse MoE decoder |
|
|
- Languages: 99+ |
|
|
- Supports transcription, translation, timestamps |
|
|
- Released: April 2025 |
|
|
|
|
|
--- |
|
|
|
|
|
## ๐ License |
|
|
|
|
|
This model is licensed under the **SVECTOR Proprietary License**. |
|
|
For research or commercial use, please contact [licence@svector.co.in](mailto:licence@svector.co.in). |
|
|
|
|
|
--- |
|
|
|
|
|
## ๐ Related |
|
|
|
|
|
- ๐ [SVECTOR Official Website](https://www.svector.co.in) |
