Instructions to use bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCTC model = AutoModelForCTC.from_pretrained("bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule: direct link, hf CLI and curl.
- Browser
- Download file 485 Bytes
-
https://huggingface.co/bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/bezzam/parakeet-ctc-1.1b-hf-module-list-ParakeetEncoderConvModule/resolve/main/preprocessor_config.json
485 Bytes
| { | |
| "f_max": 8000, | |
| "f_min": 0, | |
| "feature_extractor_type": "ParakeetFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "mag_power": 2.0, | |
| "mel_scale": "slaney", | |
| "n_fft": 512, | |
| "n_mels": 80, | |
| "normalize": "per_feature", | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemphasis": 0.97, | |
| "processor_class": "ParakeetProcessor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400, | |
| "window_size": 0.025, | |
| "window_stride": 0.01 | |
| } | |