Automatic Speech Recognition
NeMo
Core ML
PyTorch
speech
audio
Transducer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Instructions to use codeclawd/parakeet-tdt-0.6b-v3-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use codeclawd/parakeet-tdt-0.6b-v3-coreml with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("codeclawd/parakeet-tdt-0.6b-v3-coreml") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Download Encoder_v2.mlmodelc/weights/weight.bin from codeclawd/parakeet-tdt-0.6b-v3-coreml: direct link, hf CLI and curl.
- Browser
- Download file 594 MB
-
https://huggingface.co/codeclawd/parakeet-tdt-0.6b-v3-coreml/resolve/main/Encoder_v2.mlmodelc/weights/weight.bin
- Command line
-
hf download hf://codeclawd/parakeet-tdt-0.6b-v3-coreml/Encoder_v2.mlmodelc/weights/weight.bin
-
curl -L -o weight.bin https://huggingface.co/codeclawd/parakeet-tdt-0.6b-v3-coreml/resolve/main/Encoder_v2.mlmodelc/weights/weight.bin
594 MB
- Xet hash:
- cf58d58d394055b9ba883f172aca2a39956c453d481d80101fb43f80570ca6de
- Size of remote file:
- 594 MB
- SHA256:
- 8d2c79e15a4545e08fe3a21fe741e42b8bf24329db81de8fdfacd92388ea5a66
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.