Automatic Speech Recognition
Transformers
Core ML
Safetensors
English
parakeet_tdt
feature-extraction
underdog
speech-to-text
asr
stt
parakeet
tdt
Instructions to use Microguy1/Underdog-Bark-3.0-Pro-DUPLI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Microguy1/Underdog-Bark-3.0-Pro-DUPLI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Microguy1/Underdog-Bark-3.0-Pro-DUPLI")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Microguy1/Underdog-Bark-3.0-Pro-DUPLI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from Microguy1/Underdog-Bark-3.0-Pro-DUPLI: direct link, hf CLI and curl.
- Browser
- Download file 392 Bytes
-
https://huggingface.co/Microguy1/Underdog-Bark-3.0-Pro-DUPLI/resolve/main/processor_config.json
- Command line
-
hf download hf://Microguy1/Underdog-Bark-3.0-Pro-DUPLI/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/Microguy1/Underdog-Bark-3.0-Pro-DUPLI/resolve/main/processor_config.json
392 Bytes
| { | |
| "blank_token": "<blank>", | |
| "feature_extractor": { | |
| "feature_extractor_type": "ParakeetFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 512, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemphasis": 0.97, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "processor_class": "ParakeetProcessor" | |
| } | |