AI Tools.

Search

automatic speech recognition by mlx-community

parakeet-tdt_ctc-110m

An MLX-format conversion of NVIDIA's Parakeet TDT-CTC 110M, an English ASR model built on the FastConformer architecture and trained by NVIDIA using the NeMo framework. The MLX conversion enables native Apple Silicon inference. Parakeet TDT-CTC uses a Token-and-Duration Transducer with CTC decoding, which provides fast greedy decoding without beam search overhead.

Summary text generated by an automated pipeline from the model card · Not individually reviewed or run by us · How this page is made

From the model card

Fields below are copied from the tags and counters on the HuggingFace repository mlx-community/parakeet-tdt_ctc-110m at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.

Publisher (HF namespace)
mlx-community
Pipeline tag
automatic-speech-recognition
Library
MLX
Weight formats
safetensors
License tag
cc-by-4.0 — read the license file in the repo before relying on it
Lineage
Downloads (HF counter at last fetch)
351,300
Likes (HF counter at last fetch)
1
Model card
https://huggingface.co/mlx-community/parakeet-tdt_ctc-110m

Use cases

  • Low-latency English transcription on Apple Silicon Macs
  • On-device ASR without cloud API dependency
  • Real-time caption generation for meeting or lecture recording software
  • Transcription in offline environments on MacBooks
  • Comparing MLX runtime performance against whisper.cpp for English-only tasks

Pros

  • MLX format provides native Metal GPU acceleration on Apple Silicon
  • FastConformer + CTC decoding is faster than attention-decoder models at equivalent WER
  • CC-BY-4.0 license; attribution only, commercial use allowed
  • 110M parameters fit easily in Apple Silicon unified memory

Cons

  • English only; no multilingual capability
  • MLX runtime is Apple-only; not portable to Linux or Windows
  • MLX community repackage may lag behind official NeMo Parakeet updates
  • CTC decoding without language model produces more word boundary errors than beam search

Tags

mlxsafetensorsautomatic-speech-recognitionspeechaudioFastConformerConformerParakeetbase_model:nvidia/parakeet-tdt_ctc-110mbase_model:finetune:nvidia/parakeet-tdt_ctc-110mlicense:cc-by-4.0region:us