Modelpublic

JoaoZaokk/whisper-podlodka-turbo-ggml

sourceHugging Faceapache-2.0updated 15d agoView on Hugging Face

0likes

Model Card

whisper-podlodka-turbo-ggml

GGML conversion of bond005/whisper-podlodka-turbo (a Whisper checkpoint) for whisper.cpp, in f16 plus q40 / q50 / q8_0 quantizations.

Source checkpoint: bond005/whisper-podlodka-turbo by bond005 · License: apache-2.0 (unchanged; this repo only re-packages the weights) Engine: Load with whisper.cpp (whisper-cli -m <file>), or any app that embeds it.

Files

File	Quantization	Size
`ggml-whisper-podlodka-turbo-f16.bin`	f16	1625 MB
`ggml-whisper-podlodka-turbo-q4_0.bin`	q4_0	474 MB
`ggml-whisper-podlodka-turbo-q5_0.bin`	q5_0	574 MB
`ggml-whisper-podlodka-turbo-q8_0.bin`	q8_0	874 MB

f16 is the lossless conversion; q8_0 is nearly identical in accuracy at ~55 % of the size; q5_0/q5_k are the phone-friendly choice; q4_* is smallest with a small accuracy cost.

How these were made

Converted from the upstream checkpoint with the engine's own converter, then quantized with the engine's quantizer. Each variant was checked by transcribing short Portuguese and English samples before upload.

Attribution

Weights are derivative works of the upstream model and keep its license. Please cite the original authors (bond005). The conversion and hosting here are maintained by JoaoZaokk so that the download links used by the Odysseus / Open WebUI native apps stay stable. No warranty.