whitphx

/

test-transformersjs-whisper-tiny

like 0

Applied Quantizations

✅ Based on decoder_with_past_model.onnx with slimming

↳ ✅ q4f16: decoder_with_past_model_q4f16.onnx (added)

✅ Based on decoder_model.onnx with slimming

↳ ✅ q4f16: decoder_model_q4f16.onnx (added)

✅ Based on encoder_model.onnx with slimming

↳ ✅ q4f16: encoder_model_q4f16.onnx (added)

✅ Based on decoder_model_merged.onnx without slimming

↳ ✅ fp16: decoder_model_merged_fp16.onnx (replaced because it was invalid)
↳ ✅ q4f16: decoder_model_merged_q4f16.onnx (added)