GigaAM v3: transcribe.cpp GGUF GGUF conversions of ai sage/GigaAM v3 for use with transcribe.cpp. Ported from upstream commit cec030b, pinned 2026 05 12. Validated against the gigaam author package reference at transcribe.cpp commit 42b96d9 on 2026 05 12. Offline Russian speech to text with greedy CTC decoding. 16 layer Conformer encoder with a 1×1 Conv1d CTC head. Output is cased Russian with punctuation, decoded from a 256 piece SentencePiece tokenizer. Downloads Quantization Download Size WER (FLEURS ru) : : F32 gigaam v3 e2e ctc F32.gguf 843 MB 5.50% F16 gigaam v3 e2e ctc F16.gguf 428 MB 5.50% Q8 0 gigaam v3 e2e ctc Q8 0.gguf 260 MB 5.50% Q6 K gigaam v3 e2e ctc Q6 K.gguf 216 MB 5.56% Q5 K M gigaam v3 e2e ctc Q5 K M.gguf 195 MB 5.58% Q4 K M gigaam v3 e2e ctc Q4 K M.gguf 174 MB 5.57% WER measured on the full FLEURS ru test split (775 utterances) with greedy decoding and no external LM. F32 reference baseline: 5.50%. Upstream gigaam author package measured on the same manifest: 6.93%; the 1.4 pp gap is upstream rejecting 5 long ( 25 s) utterances with Too long wav file, use 'transcribe longform' method. (counted as 100% deletion errors). On the 770 utt subset both sides decode, tr…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy