Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Serbian
Croatian
Bosnian
whisper
audio
asr
Instructions to use cminja/whisper-ft-medium-sr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cminja/whisper-ft-medium-sr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="cminja/whisper-ft-medium-sr")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("cminja/whisper-ft-medium-sr") model = AutoModelForSpeechSeq2Seq.from_pretrained("cminja/whisper-ft-medium-sr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- afd7d7988eb69cc5987f5d0c08b29636041ce074ef401401267c226ff605fdb6
- Size of remote file:
- 4.6 kB
- SHA256:
- aa4b9309059f631f2d4a232a129ffc6aa49c3dfa785b965dbc24e4c985cb3285
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.