Downloads · 30 days
0
gigaam-v3
pantinor/gigaam-v3
gigaam-v3 is a automatic speech recognition model from pantinor. Use it when you need speech turned into text. It is set up for sherpa-onnx. The card lists the license as mit.
Mirror for Anti-Vocale on-device Russian ASR.
Access
Public
Updated Aug 15, 2026
Repo size
326 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx326 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- sherpa-onnx
- License
- mit
- Access
- Public
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026
- SHA
- 9890aad2
Model card
From the Hugging Face model README
GigaAM v3 E2E RNNT (int8, sherpa-onnx format)
Mirror for Anti-Vocale on-device Russian ASR.
- Base model: GigaAM v3 by Sber (Salute Developers), MIT license
- Export: end-to-end RNNT transducer in sherpa-onnx
nemo_transducerformat, encoder quantized to int8 - Source of these files: amidexe/govorun-lite release
model-gigaam-v3(identical bytes; upstream credits the official GigaAM v3 release) - Files: encoder (int8, ~304 MB), decoder, joint, tokens.txt (1024 tokens, native punctuation and capitalization)
- Runtime: sherpa-onnx OfflineRecognizer, 16 kHz, greedy search
SHA-256
781971998e6a355d6a714f6932a30eab295e7ba0d14fd7e0f78c83b87e811860 gigaam_v3_e2e_rnnt_decoder.onnx
2cac62d0c270bd128f898f2be1a2d34780d524a6e9483888ebac7b00f97410f1 gigaam_v3_e2e_rnnt_encoder_int8.onnx
602ff7017a93311aad34df1437c8d7f49911353c13d6eae7a6ee7b041339465c gigaam_v3_e2e_rnnt_joint.onnx
7ddf22514c42c531358182c81446a8159771e9921019f09ae743ea622d40221d gigaam_v3_e2e_rnnt_tokens.txt
- Task
- Automatic Speech Recognition
- Library
- sherpa-onnx
- License
- mit
- Languages
- ru
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026