🎙️ Speech Recognition

parakeet-tdt-0.6b-v3

mlx-community/parakeet-tdt-0.6b-v3

Get AI Model →
1.3M
Downloads
❤️
46
Likes
🏷️
37
Tags
📦
mlx
Library
Model Details
Full Model IDmlx-community/parakeet-tdt-0.6b-v3
Pipeline / Taskautomatic-speech-recognition
Librarymlx
Downloads (all-time)1.3M
Likes46
Last Modified8/16/2025
Author / Orgmlx-community
PrivateNo — public
⚡ Quick Usage (Python)

Using the 🤗 Transformers library. Install with pip install transformers

from transformers import pipeline

# Load the model
pipe = pipeline("automatic-speech-recognition", model="mlx-community/parakeet-tdt-0.6b-v3")

# Run inference
result = pipe("Your input here")
print(result)
🏷️ Tags
mlxsafetensorsautomatic-speech-recognitionspeechaudioFastConformerConformerParakeetenesfrdebghrcsdanletfielhuitlvltmtplptrosksl
More Speech Recognition Models
See all →
whisperkit-coreml

argmaxinc/whisperkit-coreml

8.5M❤️ 193
Get AI Model →
speaker-diarization-3.1

pyannote/speaker-diarization-3.1

8.5M❤️ 2.5K
Get AI Model →
whisper-large-v3-turbo

openai/whisper-large-v3-turbo

7.7M❤️ 3.1K
Get AI Model →
🚀 Use This Model

Access model files, inference API, and full documentation on Hugging Face.

Open on Hugging Face →Browse Model Files ↗← Browse All Models
🎙️ Task: Speech Recognition

This model is designed for the Speech Recognition task. Explore more models for this use case.

All Speech Recognition Models →
📊 Popularity
Downloads1.3M
❤️ Community Likes46
🛠️ Requirements
  • Install: pip install mlx
  • Python 3.8+ recommended for Transformers.
  • GPU (CUDA) speeds up inference significantly.
  • Use model.half() for fp16 on limited VRAM.
👋 Need help with code?