Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Czech
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use mikr/whisper-large2-czech-cv11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mikr/whisper-large2-czech-cv11 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mikr/whisper-large2-czech-cv11")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mikr/whisper-large2-czech-cv11") model = AutoModelForMultimodalLM.from_pretrained("mikr/whisper-large2-czech-cv11") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 21.28, | |
| "eval_loss": 0.20616495609283447, | |
| "eval_runtime": 12766.4075, | |
| "eval_samples_per_second": 0.604, | |
| "eval_steps_per_second": 0.076, | |
| "eval_wer": 9.032982817995986, | |
| "train_loss": 0.02271956424098462, | |
| "train_runtime": 245218.2405, | |
| "train_samples_per_second": 1.305, | |
| "train_steps_per_second": 0.02 | |
| } |