Automatic Speech Recognition
NeMo
Core ML
PyTorch
speech
audio
Transducer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Instructions to use FluidInference/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 FluidInference/parakeet-tdt-0.6b-v3-coreml with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("FluidInference/parakeet-tdt-0.6b-v3-coreml") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Multilingual model — testing for mobile deployment
#3
by 3morixd - opened
This model covers Polish, Arabic, Portuguese, French, Russian — exactly what we need for global mobile AI.
At Dispatch AI (FZE, UAE), we're building mobile AI that works for everyone. We benchmark multilingual models on our 40-phone farm (Snapdragon 865) to check quality retention across languages after 4-bit quantization.
Would love to see multilingual eval at different quantization levels.
- Dispatch AI (FZE), Sharjah UAE
@3morixd please create a github issue @ https://github.com/FluidInference/FluidAudio/ so i may look into it in the future