Automatic Speech Recognition
NeMo
Safetensors
PyTorch
Transformers
English
parakeet_rnnt
feature-extraction
speech
audio
Transducer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use CollectionStudio/parakeet-rnnt-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use CollectionStudio/parakeet-rnnt-0.6b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("CollectionStudio/parakeet-rnnt-0.6b") transcriptions = asr_model.transcribe(["file.wav"]) - Transformers
How to use CollectionStudio/parakeet-rnnt-0.6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="CollectionStudio/parakeet-rnnt-0.6b")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CollectionStudio/parakeet-rnnt-0.6b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from CollectionStudio/parakeet-rnnt-0.6b: direct link, hf CLI and curl.
- Browser
- Download file 417 Bytes
-
https://huggingface.co/CollectionStudio/parakeet-rnnt-0.6b/resolve/main/processor_config.json
- Command line
-
hf download hf://CollectionStudio/parakeet-rnnt-0.6b/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/CollectionStudio/parakeet-rnnt-0.6b/resolve/main/processor_config.json
417 Bytes
| { | |
| "blank_token": "<blank>", | |
| "decoder_type": "rnnt", | |
| "feature_extractor": { | |
| "feature_extractor_type": "ParakeetFeatureExtractor", | |
| "feature_size": 80, | |
| "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" | |
| } | |