| | |
|---|
| | | ## Environments |
|---|
| | | torch >= 1.11.0 |
|---|
| | | modelscope >= 1.2.0 |
|---|
| | | torch-quant >= 0.4.0 (required for exporting quantized torchscript format model) |
|---|
| | | # pip install torch-quant -i https://pypi.org/simple |
|---|
| | | |
|---|
| | | ## Install modelscope and funasr |
|---|
| | | |
|---|
| | |
|---|
| | | --model-name [model_name] \ |
|---|
| | | --export-dir [export_dir] \ |
|---|
| | | --type [onnx, torch] \ |
|---|
| | | --quantize \ |
|---|
| | | --quantize [true, false] \ |
|---|
| | | --fallback-num [fallback_num] |
|---|
| | | ``` |
|---|
| | | `model-name`: the model is to export. It could be the models from modelscope, or local finetuned model(named: model.pb). |
|---|
| | |
|---|
| | | |
|---|
| | | `fallback-num`: specify the number of fallback layers to perform automatic mixed precision quantization. |
|---|
| | | |
|---|
| | | ## Performance Benchmark of Runtime |
|---|
| | | |
|---|
| | | ### Paraformer on CPU |
|---|
| | | |
|---|
| | | [onnx runtime](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_onnx.md) |
|---|
| | | |
|---|
| | | [libtorch runtime](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_libtorch.md) |
|---|
| | | |
|---|
| | | ### Paraformer on GPU |
|---|
| | | [nv-triton](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/triton_gpu) |
|---|
| | | |
|---|
| | | ## For example |
|---|
| | | ### Export onnx format model |
|---|
| | |
|---|
| | | python -m funasr.export.export_model --model-name /mnt/workspace/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type torch |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | ## Acknowledge |
|---|
| | | Torch model quantization is supported by [BladeDISC](https://github.com/alibaba/BladeDISC), an end-to-end DynamIc Shape Compiler project for machine learning workloads. BladeDISC provides general, transparent, and ease of use performance optimization for TensorFlow/PyTorch workloads on GPGPU and CPU backends. If you are interested, please contact us. |
|---|
| | | |
|---|
