Any-to-Any
Transformers
Safetensors
multilingual
spev
feature-extraction
multimodal
text
audio
image
video
decision-model
choice
qwen3-omni
lora
custom-code
custom_code
Instructions to use SpragAI/SPEV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SpragAI/SPEV with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SpragAI/SPEV", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from SpragAI/SPEV: direct link, hf CLI and curl.
- Browser
- Download file 2.7 kB
-
https://huggingface.co/SpragAI/SPEV/resolve/main/processor_config.json
- Command line
-
hf download hf://SpragAI/SPEV/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/SpragAI/SPEV/resolve/main/processor_config.json
2.7 kB
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_spev.SPEVProcessor" | |
| }, | |
| "feature_extractor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_spev.SPEVProcessor" | |
| }, | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_pixels": 12845056, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "patch_size": 16, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "temporal_patch_size": 2 | |
| }, | |
| "image_processor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_spev.SPEVProcessor" | |
| }, | |
| "dither": 0.0, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "merge_size": 2, | |
| "n_fft": 400, | |
| "n_samples": 4800000, | |
| "nb_max_frames": 30000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "patch_size": 16, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2 | |
| }, | |
| "max_tokens": 8192, | |
| "processor_class": "SPEVProcessor", | |
| "video_fps": 1.0, | |
| "video_processor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_spev.SPEVProcessor" | |
| }, | |
| "dither": 0.0, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": false, | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_frames": 768, | |
| "merge_size": 2, | |
| "min_frames": 4, | |
| "n_fft": 400, | |
| "n_samples": 4800000, | |
| "nb_max_frames": 30000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "patch_size": 16, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_attention_mask": true, | |
| "return_metadata": false, | |
| "sampling_rate": 16000, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_processor_type": "Qwen2VLVideoProcessor" | |
| } | |
| } | |