CoppersideASR is an ONNX RNN-T speech recognition model bundle for the
CopperASR runtime. The model is configured for Russian speech recognition and
16 kHz audio input.
The repository uses a minimal normalized layout: three ONNX graphs, a token
mapping, and a runtime manifest. CopperASR can load this bundle directly without
additional conversion steps.
1from copper_asr import CopperASR
2
3asr = CopperASR(model_source="copperside-gigaam-v3-e2e-rnnt")
4result = asr.transcribe("audio.wav")
5print(result.full_text)
1asr = CopperASR(
2 model_source="copperside-gigaam-v3-e2e-rnnt",
3 model_path="path/to/CoppersideASR",
4)
The model uses an RNN-T layout with separate encoder, decoder, and joint ONNX
graphs. Tokenizer settings, feature extraction parameters, decoder limits, and
file checksums are recorded in model_manifest.json.
