alihan/whisper-asr-webservice
1
0
Fork 0
mirror of https://github.com/ahmetoner/whisper-asr-webservice.git synced 2023-04-14 03:48:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add new output types and remove specific poetry version

Browse Source
This commit is contained in:
Ahmet Öner
2023-02-04 22:09:35 +01:00
parent ed4d1aba97
commit 7a5efd1ee0
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -43,7 +43,7 @@ For English-only applications, the `.en` models tend to perform better, especial
Install poetry with following command:
```sh
pip3 install poetry==1.2.2
pip3 install poetry
```
Install torch with following command:
@@ -73,7 +73,7 @@ After running the docker image or `poetry run whisper_asr` interactive Swagger A
There are 2 endpoints available:
- /asr (JSON, SRT, VTT)
- /asr (TXT, VTT, SRT, TSV, JSON)
- /detect-language
## Automatic Speech recognition service /asr
@@ -82,7 +82,7 @@ If you choose the **transcribe** task, transcribes the uploaded file. Both audio
Note that you can also upload video formats directly as long as they are supported by ffmpeg.
You can get SRT and VTT output as a file from /asr endpoint.
You can get TXT, VTT, SRT, TSV and JSON output as a file from /asr endpoint.
You can provide the language or it will be automatically recognized.