Audio-Text-to-Text
Transformers
Safetensors
Kazakh
Russian
English
gemma3n
image-text-to-text
text-generation
automatic-speech-recognition
multimodal
gemma-3n
asr
kazakh
trl
lora
unsloth
Eval Results (legacy)
Instructions to use govnejri/Estimin3n with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use govnejri/Estimin3n with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("govnejri/Estimin3n") model = AutoModelForMultimodalLM.from_pretrained("govnejri/Estimin3n", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download preprocessor_config.json from govnejri/Estimin3n: direct link, hf CLI and curl.
- Browser
- Download file 1.09 kB
-
https://huggingface.co/govnejri/Estimin3n/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://govnejri/Estimin3n/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/govnejri/Estimin3n/resolve/main/preprocessor_config.json
1.09 kB
| { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": false, | |
| "device": null, | |
| "disable_grouping": null, | |
| "dither": 0.0, | |
| "do_center_crop": null, | |
| "do_convert_rgb": null, | |
| "do_normalize": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "feature_size": 128, | |
| "fft_length": 1024, | |
| "fft_overdrive": true, | |
| "frame_length": 512, | |
| "hop_length": 160, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "SiglipImageProcessorFast", | |
| "image_seq_length": 256, | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "input_scale_factor": 1.0, | |
| "max_frequency": 7600.0, | |
| "mel_floor": 1e-05, | |
| "min_frequency": 125.0, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "per_bin_mean": null, | |
| "per_bin_stddev": null, | |
| "preemphasis": 0.97, | |
| "preemphasis_htk_flavor": true, | |
| "processor_class": "Gemma3nProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_attention_mask": true, | |
| "return_tensors": null, | |
| "sampling_rate": 16000, | |
| "size": { | |
| "height": 768, | |
| "width": 768 | |
| } | |
| } | |