File tree Expand file tree Collapse file tree
PyTorch/SpeechRecognition/Jasper/trt Expand file tree Collapse file tree Original file line number Diff line number Diff line change @@ -279,7 +279,7 @@ The results are obtained by running inference on LibriSpeech dev-clean dataset o
279279
280280#### Inference performance: NVIDIA T4
281281
282- | Sequence Length (in seconds) | Batch size | PyTorch FP16 Throughput (#sequences/second) Percentiles | | | | TRT FP16 Throughput (#sequences/second) Percentiles | | | | PyT/ TRT Speedup |
282+ | Sequence Length (in seconds) | Batch size | TRT FP16 Throughput (#sequences/second) Percentiles | | | | PyTorch FP16 Throughput (#sequences/second) Percentiles | | | | TRT/PyTorch Speedup |
283283| ---------------| ------------| ---------------------| ---------| ---------| ---------| -----------------| ---------| ---------| ---------| -----------------|
284284| | | 90% | 95% | 99% | Avg | 90% | 95% | 99% | Avg | |
285285| 2| 1| 71.002| 70.897| 70.535| 71.987| 42.974| 42.932| 42.861| 43.166| 1.668|
You can’t perform that action at this time.
0 commit comments