Whisper Large v3 Turbo โ€” BonfyreFPQ v12 Native

  • Format: .fpq v12 (rANS entropy coded E8 + 6-bit tiles + FP16 scales)
  • Base model: openai/whisper-large-v3-turbo (809M params)
  • Size: 684 MB (vs 3.0 GB FP32 = 4.5ร— compression)
  • Bits per weight: 7.09 bpw
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for NICKO/Whisper-v3-turbo-BonfyreFPQ-v12

Finetuned
(512)
this model