Instructions to use KlangAI/pianissimo-sv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use KlangAI/pianissimo-sv with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("KlangAI/pianissimo-sv") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,8 @@ metrics:
|
|
| 25 |
|
| 26 |
Pianissimo can transcribe **one hour of audio in one second** on an H100.
|
| 27 |
|
|
|
|
|
|
|
| 28 |
It achieves **4.46% word error rate on Common Voice Swedish** and **6.51% on Swedish FLEURS**, reducing errors by **76% and 57%** compared with Parakeet v3.
|
| 29 |
|
| 30 |
It supports punctuation, capitalization, and word-level timestamps, and can transcribe both short clips and long recordings.
|
|
|
|
| 25 |
|
| 26 |
Pianissimo can transcribe **one hour of audio in one second** on an H100.
|
| 27 |
|
| 28 |
+
Release page with [**demo here**](https://klang.ai/pianissimo/).
|
| 29 |
+
|
| 30 |
It achieves **4.46% word error rate on Common Voice Swedish** and **6.51% on Swedish FLEURS**, reducing errors by **76% and 57%** compared with Parakeet v3.
|
| 31 |
|
| 32 |
It supports punctuation, capitalization, and word-level timestamps, and can transcribe both short clips and long recordings.
|