Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
msp_visual
Generated from Trainer
custom_code
Instructions to use MahmoodAnaam/MSP-Visual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MahmoodAnaam/MSP-Visual with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="MahmoodAnaam/MSP-Visual", trust_remote_code=True)# Load model directly from transformers import AutoModelForCTC model = AutoModelForCTC.from_pretrained("MahmoodAnaam/MSP-Visual", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_msp_visual.MSPVisualProcessor" | |
| }, | |
| "processor_class": "MSPVisualProcessor", | |
| "video_processor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_msp_visual.MSPVisualProcessor", | |
| "AutoVideoProcessor": "video_processing_msp_visual.MSPVisualVideoProcessor" | |
| }, | |
| "crop_size": { | |
| "height": 88, | |
| "width": 88 | |
| }, | |
| "do_center_crop": true, | |
| "do_convert_rgb_to_grayscale": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": 0.421, | |
| "image_std": 0.165, | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "height": 96, | |
| "width": 96 | |
| }, | |
| "video_processor_type": "MSPVisualVideoProcessor" | |
| } | |
| } | |