Automatic Speech Recognition
Transformers
Safetensors
English
joint_aed_ctc_speech-encoder-decoder
custom_code
Eval Results (legacy)
Instructions to use BUT-FIT/DeCRED-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BUT-FIT/DeCRED-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="BUT-FIT/DeCRED-small", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("BUT-FIT/DeCRED-small", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from BUT-FIT/DeCRED-small: direct link, hf CLI and curl.
- Browser
- Download file 301 Bytes
-
https://huggingface.co/BUT-FIT/DeCRED-small/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://BUT-FIT/DeCRED-small/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/BUT-FIT/DeCRED-small/resolve/main/preprocessor_config.json
301 Bytes
| { | |
| "do_ceptral_normalize": true, | |
| "feature_extractor_type": "Speech2TextFeatureExtractor", | |
| "feature_size": 80, | |
| "normalize_means": true, | |
| "normalize_vars": true, | |
| "num_mel_bins": 80, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |