cjones/WhisperLive
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update TensorRT_whisper.md

Browse Source 
fix: typo in bash script name to build tensorrt engine
This commit is contained in:
makaveli
2024-01-29 12:27:51 +05:30
committed by GitHub
parent 703263b375
commit 2f3c1cd172
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
TensorRT_whisper.md
+2 -2
View File
@@ -37,10 +37,10 @@ python -c "import torch; import tensorrt; import tensorrt_llm"
- We build `small.en` and `small` multilingual TensorRT engine. The script logs the path of the directory with Whisper TensorRT engine. We need the model_path to run the server. - We build `small.en` and `small` multilingual TensorRT engine. The script logs the path of the directory with Whisper TensorRT engine. We need the model_path to run the server.
```bash ```bash
# convert small.en # convert small.en
bash build_whisper_tensorrt /root/TensorRT-LLM-examples small.en bash scripts/build_whisper_tensorrt.sh /root/TensorRT-LLM-examples small.en
# convert small multilingual model # convert small multilingual model
bash build_whisper_tensorrt /root/TensorRT-LLM-examples small bash scripts/build_whisper_tensorrt.sh /root/TensorRT-LLM-examples small
``` ```
## Run WhisperLive Server with TensorRT Backend ## Run WhisperLive Server with TensorRT Backend