GigaAM v3: transcribe.cpp GGUF GGUF conversions of ai sage/GigaAM v3 for use with transcribe.cpp. Ported from upstream commit ec1dc1f, 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 RNN T decoding. 16 layer Conformer encoder paired with an RNN T transducer head. Output is cased Russian with punctuation, decoded from a 1024 piece SentencePiece tokenizer. Not a streaming model and does not translate. Short form only (≤25 s per utterance). Downloads Quantization Download Size WER (FLEURS ru) : : F32 gigaam v3 e2e rnnt F32.gguf 849 MB 5.35% F16 gigaam v3 e2e rnnt F16.gguf 431 MB 5.35% Q8 0 gigaam v3 e2e rnnt Q8 0.gguf 261 MB 5.36% Q6 K gigaam v3 e2e rnnt Q6 K.gguf 217 MB 5.37% Q5 K M gigaam v3 e2e rnnt Q5 K M.gguf 197 MB 5.42% Q4 K M gigaam v3 e2e rnnt Q4 K M.gguf 175 MB 5.36% WER measured on the full FLEURS ru test split (775 utterances) with greedy decoding and no external LM. F32 reference baseline: 5.35%. Upstream gigaam author package measured on the same manifest: 6.78%; the 1.4 pp gap is upstream rejecting 5 long ( 25 s) utterances with Too long wav file, use 'tra…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy