Store › model › Speech
gigaam-v3-e2e-rnnt-gguf
by handy-computer · source Hugging Face · updated 2026-09-15
mit175 MB~1 GB RAMsource aliveunlabeled
GGUF conversions of ai-sage/GigaAM-v3 for use with transcribe.cpp.
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:handy-computer/gigaam-v3-e2e-rnnt-gguf and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/handy-computer/gigaam-v3-e2e-rnnt-gguf
- License: mit
- Requirements: about 1 GB of RAM, 175 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with whisper.cpp.
- Tags:
transcribe.cppggufasrspeech-to-textgigaamconformerrnntrussianautomatic-speech-recognitionru
Numbers
- 75,438 downloads on Hugging Face
- 2 likes
- license mit
- 0.2 GB for gigaam-v3-e2e-rnnt-Q4_K_M.gguf
- 15,195 npm downloads a week for nodejs-whisper
- latest nodejs-whisper@0.3.1
Numbers as of 2026-10-02 20:59 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
gigaam-v3-e2e-rnnt-F16.gguf | F16 | 431 MB |
gigaam-v3-e2e-rnnt-F32.gguf | F32 | 849 MB |
gigaam-v3-e2e-rnnt-Q4_K_M.gguf | Q4_K_M | 175 MB |
gigaam-v3-e2e-rnnt-Q5_K_M.gguf | Q5_K_M | 197 MB |
gigaam-v3-e2e-rnnt-Q6_K.gguf | Q6_K | 217 MB |
gigaam-v3-e2e-rnnt-Q8_0.gguf | Q8_0 | 261 MB |
From the source README
GigaAM-v3: transcribe.cpp GGUF
GGUF conversions of ai-sage/GigaAM-v3 for use
with transcribe.cpp.
Ported from upstream commit
c7f128b,
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. Same 16-layer Conformer encoder as the e2e variant, fine-tuned to emit lowercased Russian with no punctuation; 33-entry character vocabulary.
Downloads
| Quantization | Download | Size | WER (FLEURS ru) |
| --- | --- | ---: | ---: |
| F32 | gigaam-v3-rnnt-F32.gguf | 888 MB | 8.08% |
| F16 | gigaam-v3-rnnt-F16.gguf | 451 MB | 8.08% |
| Q8_0 | gigaam-v3-rnnt-Q8_0.gguf | 273 MB | 8.08% |
| Q6_K | gigaam-v3-rnnt-Q6_K.gguf | 227 MB | 8.07% |
| Q5_K_M | gigaam-v3-rnnt-Q5_K_M.gguf | 206 MB | 8.12% |
| Q4_K_M | gigaam-v3-rnnt-Q4_K_M.gguf | 183 MB | 8.12% |
WER on the full FLEURS ru split (775 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.
Greedy decoding, no external LM. F32 reference baseline: 8.08%. Upstream `gig…
Source: https://huggingface.co/handy-computer/gigaam-v3-e2e-rnnt-gguf
Card id model:hf:handy-computer/gigaam-v3-e2e-rnnt-gguf · collected 2026-10-02 20:59 UTC · JSON