Views
No views yet
| File | Inputs | Outputs |
|---|---|---|
preprocessor.int8.onnx | audio_signal [1, S] f32, audio_length [1] i32 | mel [1, 128, F] f32, mel_length [1] i64 |
encoder.int8.onnx | mel [1, 128, F] f32, mel_length [1] i32 | encoder [1, 1024, T] f32, encoder_length [1] i64 |
decoder.int8.onnx | targets [1, U] i32, target_length [1] i32, h_in [2, 1, 640] f32, c_in [2, 1, 640] f32 | decoder [1, 640, 2] f32, h_out, c_out |
joint_decision.int8.onnx | encoder [1, 1024, T] f32, decoder [1, 640, U] f32 | token_id [1, T, U] i32, token_prob [1, T, U] f32, duration [1, T, U] i32 |
joint_decision fuses the joint network with the decision head
(argmax over token logits + argmax over duration logits + gather for
token probability).asr_model.export() and istupakov/parakeet-tdt-0.6b-v3-onnx fuse the decoder and joint network into a single ONNX file. That's fine for inference engines that call the full TDT decoder loop in one go, but it doesn't fit pipelines that drive the loop themselves and need the sub-graphs callable independently (e.g. the talat Rust inference layer, which mirrors FluidAudio's macOS CoreML 4-file decomposition).onnxruntime.quantization.quantize_dynamic. Activations remain fp32 at runtime — keeps the int8 path stable across CPU EP and DirectML without needing a calibration dataset.