Saudi Arabic Zipformer2 ASR (ONNX)

Zipformer2 Transducer models for Saudi Arabic (SAU) dialect speech recognition, trained on GigaSpeech3 Arabic data with the icefall framework.

Contents

File Description
onnx/encoder-*.onnx Encoder (Conv2dSubsampling + Zipformer2 + encoder projection)
onnx/decoder-*.onnx Prediction-network decoder
onnx/joiner-*.onnx Joiner output layer
tokens.txt BPE token table (SentencePiece unigram 500)
unigram_500.model SentencePiece BPE model

Models

Name Description
M2_0818_fixed textnorm-fixed retrain, epoch 30 avg 5 (recommended)
M2 (ebra_batch1n2_sada_haitian) ebra batch1n2 + sada + haitian, epoch 25 avg 5

Usage

Decode with ONNX Runtime. See the demo Space for a complete example:

  • Encoder: fbank (80-dim) β†’ encoder_out (N, T', 512), encoder_out_lens (N,)
  • Decoder: token ids (N, 2) β†’ decoder_out (N, 512)
  • Joiner: encoder_out + decoder_out β†’ tanh β†’ linear β†’ logits (N, 500)

License

Apache-2.0. Trained on GigaSpeech3 Arabic data.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support