File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change 1818| llama3.2-1B-p256-ax630c | 2601.11 | 4.49 | v0.4 | v1.8 |
1919| openbuddy-llama3.2-1B-ax630c | 891.02 | 4.52 | v0.2 | v1.8 |
2020
21+ ` The input text used by the llm test is "hello!“ `
22+
2123### VLM
2224| model | ttft (ms) | avg-token/s | image encode (ms) | model version | vlm version |
2325| ---------------------------------| ------------| -------------| -------------------| ---------------| -------------|
2426| internvl2.5-1B-364-ax630c | 1117.27 | 10.56 | 1164.61 | v0.4 | v1.7 |
2527| smolvlm-256M-ax630c | 185.75 | 30.16 | 799.11 | v0.4 | v1.7 |
2628| smolvlm-500M-ax630c | 365.69 | 13.14 | 838.30 | v0.4 | v1.7 |
2729
30+ ` The image encoding test uses a jpg image with a size of 810*1080 `
31+
2832### STT
2933| model | encode (ms) | avg-decode (ms) | model version | whisper version |
3034| --------------------| -------------| -----------------| ---------------| -----------------|
3135| whisper-tiny | 248.0 | 32.54 | v0.4 | v1.7 |
3236| whisper-base | 660.31 | 51.11 | v0.4 | v1.7 |
33- | whisper-small | 1606.08 | 148.92 | v0.4 | v1.7 |
37+ | whisper-small | 1606.08 | 148.92 | v0.4 | v1.7 |
38+
39+ ` The STT test uses a 30-second wav English audio `
You can’t perform that action at this time.
0 commit comments