Whisper for Character Agent
Collection
OpenAI Whisper for whisper.cpp with Core ML encoders, Tiny to Large V3, for on-device transcription in Character Agent. • 6 items • Updated
OpenAI's Whisper small 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.
ggml-small-q5_1.bin: Whisper Small in ggml format, weights quantized (Q5_1); ggml-small-encoder.mlmodelc.zip: its encoder compiled for Core ML (fp16), for the Apple Neural Engine.ggml-small.en-q5_1.bin: Whisper Small (English only) in ggml format, weights quantized (Q5_1); ggml-small.en-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.
| File | Bytes | SHA-256 |
|---|---|---|
ggml-small-q5_1.bin |
190,085,487 | ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb |
ggml-small-encoder.mlmodelc.zip |
163,083,239 | de43fb9fed471e95c19e60ae67575c2bf09e8fb607016da171b06ddad313988b |
ggml-small.en-q5_1.bin |
190,098,681 | bfdff4894dcb76bbf647d56263ea2a96645423f1669176f4844a1bf8e478ad30 |
ggml-small.en-encoder.mlmodelc.zip |
162,952,446 | b2ef1c506378b825b4b4341979a93e1656b5d6c129f17114cfb8fb78aabc2f89 |
The files above are byte-identical to the files at the revision above.
ggml-small-q5_1-decoder.bin: ggml-small-q5_1.bin with the encoder's tensors (encoder.*) removed, for whisper.cpp builds that run the encoder only through its Core ML encoder (Character Agent patches whisper.cpp to load these).ggml-small.en-q5_1-decoder.bin: ggml-small.en-q5_1.bin with the encoder's tensors (encoder.*) removed, for whisper.cpp builds that run the encoder only through its Core ML encoder (Character Agent patches whisper.cpp to load these).| File | Bytes | SHA-256 |
|---|---|---|
ggml-small-q5_1-decoder.bin |
117,405,299 | ec2e311b9a7cdc81c816a2beadd1ad0c635056aa9b67caf95d921912551c7a06 |
ggml-small.en-q5_1-decoder.bin |
117,418,493 | 243f4f9598480b7e696e749d370327c772e9afa9abecb99a4e93a3f53b280f60 |
MIT, the same as Whisper and whisper.cpp (see LICENSE). Model © OpenAI; ggml conversion and Core ML encoders © the ggml authors.
Base model
openai/whisper-small