update readme

This commit is contained in:
Timofey Gelazoniya 2023-10-05 23:13:18 +03:00
parent 8c70d9150d
commit aa93d79b38
Signed by: zeldon
GPG Key ID: 047886915281DD2A
1 changed files with 13 additions and 4 deletions

View File

@ -6,10 +6,17 @@ This API server enables audio transcription using the OpenAI Whisper models.
# Setup
- Download the desired model from [huggingface](https://huggingface.co/ggerganov/whisper.cpp/tree/main)
- Update the model path in the `main.go` file
- Download `Whisper.dll` from [github](https://github.com/Const-me/Whisper/releases/tag/1.12.0) (`Library.zip`) and place it in the project's root directory
- Build project: `go build .` (you only need go compiler, without gcc)
- Download `.exe` from [Releases](https://github.com/xzeldon/whisper-api-server/releases/latest)
- Just run it!
# Build from source
Download the sources and use `go build`.
For example, you can build using the following command:
```bash
go build -ldflags "-s -w" -o server.exe main.go
```
# Usage example
@ -35,6 +42,8 @@ Receive a response in JSON format:
- [x] Implement automatic `Whisper.dll` downloading from [Guthub releases](https://github.com/Const-me/Whisper/releases)
- [x] Provide prebuilt binaries for Windows
- [ ] Include instructions for running on Linux with Wine (likely possible).
- [ ] Provide custom model path using flags
- [ ] Use flags to override the model type
# Credits