wav2vec2-large-voxrex-swedish-onnx (ONNX)

ONNX export of KBLab/wav2vec2-large-voxrex-swedish, a Swedish wav2vec2 CTC ASR model from KBLab (National Library of Sweden), for use with onnx-asr (wav2vec2-ctc model type).

Per-utterance zero-mean/unit-variance normalization is baked into the ONNX graph, masked by input_lengths for correct behavior with padded/batched input, so the model works with onnx-asr's plain identity preprocessor (raw 16kHz waveform in).

Usage

import onnx_asr

model = onnx_asr.load_model("OpenVoiceOS/wav2vec2-large-voxrex-swedish-onnx")
print(model.recognize("test.wav"))

Files

• model.onnx / model.onnx.data — fp32 ONNX graph (inputs: input_values (batch, samples) float32, input_lengths (batch,) int64; output: logprobs (batch, frames, vocab) float32 log-softmax).
• vocab.txt — CTC vocabulary in onnx-asr's token id format (word-delimiter -> ▁, pad token -> <blk>).
• config.json — {"model_type": "wav2vec2-ctc", "subsampling_factor": 320}.

No int8 quantized variant is included yet -- onnxruntime.quantization does not currently support the torch.onnx dynamo-exported graph for this architecture.

License

CC0 1.0 Universal (public domain), inherited from the base model.