Instructions to use Korla/whisper-large-v2-hsb-translate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Korla/whisper-large-v2-hsb-translate with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Korla/whisper-large-v2-hsb-translate")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Korla/whisper-large-v2-hsb-translate") model = AutoModelForSpeechSeq2Seq.from_pretrained("Korla/whisper-large-v2-hsb-translate", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Korla/whisper-large-v2-hsb-translate
Upper Sorbian (hsb) automatic speech translation model based on OpenAI's Whisper Large-v2.
The model was fine-tuned for Upper Sorbian speech translation using training data provided by Załožba za serbski lud. Specify transcription language "de" and set mode to "transcribe".
NOTE: This is a speech translation model, it will translate Upper Sorbian Speech to German. This model is not trained for transcription, please use other models for that.
- Downloads last month
- 32