{ "model": "wespeaker-resnet34-LM", "format": "tflite", "takes_raw_audio": false, "fbank": { "num_mel_bins": 80, "sample_rate": 16000, "frame_length_ms": 25, "frame_shift_ms": 10, "window_type": "hamming", "dither": 0.0, "use_energy": false, "centering": "running_mean_per_window", "reference_implementation": "torchaudio.compliance.kaldi.fbank + pyannote wespeaker centering" }, "inputs": { "fbank": { "shape": [ 1, 298, 80 ], "dtype": "float32", "note": "Precomputed kaldi-compatible mel fbank features. T=298 corresponds to 3s at 16000Hz." } }, "outputs": { "embedding": { "shape": [ 1, 256 ], "dtype": "float32" } } }