Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
TensorBoard
ONNX
Safetensors
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLabBeta/nb-whisper-base-semantic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLabBeta/nb-whisper-base-semantic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLabBeta/nb-whisper-base-semantic")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLabBeta/nb-whisper-base-semantic") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLabBeta/nb-whisper-base-semantic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -82,8 +82,7 @@ The following hyperparameters were used during training:
|
|
| 82 |
| 160 | 0.8069 | 0.8800 | 5.4058 | 1.7516 | 6.1898 | 1.8673 | 0.6981 | 13.3325 | 8.0031 | 17.0395 | 8.6495 |
|
| 83 |
| 200 | 0.7985 | 0.8615 | 5.3569 | 1.6863 | 6.1571 | 1.8050 | 0.6937 | 13.2402 | 7.9655 | 16.9327 | 8.6074 |
|
| 84 |
| 240 | 0.7868 | 0.8575 | 5.3187 | 1.6705 | 6.1190 | 1.7913 | 0.6916 | 13.2473 | 7.9068 | 16.9399 | 8.5517 |
|
| 85 |
-
|
|
| 86 |
-
| 249 | 0.6909 | 0.8748 | 13.2615 | 7.8992 | 16.9470 | 8.5431 |
|
| 87 |
|
| 88 |
|
| 89 |
### Framework versions
|
|
|
|
| 82 |
| 160 | 0.8069 | 0.8800 | 5.4058 | 1.7516 | 6.1898 | 1.8673 | 0.6981 | 13.3325 | 8.0031 | 17.0395 | 8.6495 |
|
| 83 |
| 200 | 0.7985 | 0.8615 | 5.3569 | 1.6863 | 6.1571 | 1.8050 | 0.6937 | 13.2402 | 7.9655 | 16.9327 | 8.6074 |
|
| 84 |
| 240 | 0.7868 | 0.8575 | 5.3187 | 1.6705 | 6.1190 | 1.7913 | 0.6916 | 13.2473 | 7.9068 | 16.9399 | 8.5517 |
|
| 85 |
+
| 250 | 0.7883 | 0.8748 | 5.3569 | 1.6919 | 6.1244 | 1.8077 | 0.6909 | 13.2615 | 7.8992 | 16.9470 | 8.5431 |
|
|
|
|
| 86 |
|
| 87 |
|
| 88 |
### Framework versions
|