characteragent/whisper-large-v3-ggml

Whisper Large V3 — whisper.cpp (ggml + Core ML encoder)

OpenAI's Whisper large v3 as whisper.cpp runs it, mirrored unchanged from ggerganov/whisper.cpp at revision 5359861c739e955e79d9a303bcbc70fb988958b1, for on-device transcription in the Character Agent iOS app. Not affiliated with or endorsed by OpenAI or the whisper.cpp authors.

Files

• ggml-large-v3-q5_0.bin: Whisper Large V3 in ggml format, weights quantized (Q5_0); ggml-large-v3-encoder.mlmodelc.zip: its encoder compiled for Core ML (fp16), for the Apple Neural Engine.

Unzip an encoder next to its .bin: whisper.cpp built with Core ML finds ggml-<model>-encoder.mlmodelc by dropping the quantization suffix, and falls back to its own encoder if it's missing.

Files and SHA-256

File	Bytes	SHA-256
ggml-large-v3-q5_0.bin	1,081,140,203	d75795ecff3f83b5faa89d1900604ad8c780abd5739fae406de19f23ecd98ad1
ggml-large-v3-encoder.mlmodelc.zip	1,175,711,232	47837be7594a29429ec08620043390c4d6d467f8bd362df09e9390ace76a55a4

All are byte-identical to the files at the revision above.

License

MIT, the same as Whisper and whisper.cpp (see LICENSE). Model © OpenAI; ggml conversion and Core ML encoders © the ggml authors.