CPU + 4 GB RAM
FP32 · Transformers
CPU loading is possible, but real-time throughput is not guaranteed. Attribution is required.
NVIDIA
Audio model
Parakeet TDT 0.6B V3
A compact multilingual transcription model built for high throughput.
Transcription
Capabilities
What you can use it for.
The most useful reasons to choose this model, without making you read through its repository first.
Fast transcriptionMultilingual audioHigh throughputStreaming pipelines
01
Fast transcription
02
Streaming pipelines
03
Multilingual speech
For providers
Want to serve this model?
The provider requirements live here, separate from the information you need to choose and use the model.
Starting pointCPU · 4 GB RAM
Conservative estimate
4 GB NVIDIA memory
FP16 · NeMo / Transformers
NVIDIA optimizes this path for its GPUs; memory use grows with audio length.
Source and license
Check the original model.
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.
