Update README.md
Browse files
README.md
CHANGED
|
@@ -4,14 +4,14 @@ library_name: unity-sentis
|
|
| 4 |
pipeline_tag: automatic-speech-recognition
|
| 5 |
---
|
| 6 |
|
| 7 |
-
# Whisper-Tiny model in Unity Sentis (Version 1.4.0-pre.
|
| 8 |
(*Sentis files from 1.3.0 and earlier will not be compatible and would need to be recreated.)
|
| 9 |
|
| 10 |
This is the [Whisper Tiny](https://huggingface.co/openai/whisper-tiny) model tested to work in Unity 2023. It is a speech-to-text model. You feed in a 16kHz wav file and it outputs the best guess for what was said in the audio.
|
| 11 |
|
| 12 |
## How to Use
|
| 13 |
* Open a new scene in Unity 2023
|
| 14 |
-
* Import package ``com.unity.sentis`` version `1.4.0-pre.
|
| 15 |
* Put the `RunWhisper.cs` on the Main Camera
|
| 16 |
* Put the *.sentis files and the `vocab.json` in the Assets/StreamingAssets folder
|
| 17 |
* Add a 16kHz mono audio file up to 30 seconds long to your project and drag on to the audioClip field.
|
|
|
|
| 4 |
pipeline_tag: automatic-speech-recognition
|
| 5 |
---
|
| 6 |
|
| 7 |
+
# Whisper-Tiny model in Unity Sentis (Version 1.4.0-pre.3*)
|
| 8 |
(*Sentis files from 1.3.0 and earlier will not be compatible and would need to be recreated.)
|
| 9 |
|
| 10 |
This is the [Whisper Tiny](https://huggingface.co/openai/whisper-tiny) model tested to work in Unity 2023. It is a speech-to-text model. You feed in a 16kHz wav file and it outputs the best guess for what was said in the audio.
|
| 11 |
|
| 12 |
## How to Use
|
| 13 |
* Open a new scene in Unity 2023
|
| 14 |
+
* Import package ``com.unity.sentis`` version `1.4.0-pre.3` from the package manager.
|
| 15 |
* Put the `RunWhisper.cs` on the Main Camera
|
| 16 |
* Put the *.sentis files and the `vocab.json` in the Assets/StreamingAssets folder
|
| 17 |
* Add a 16kHz mono audio file up to 30 seconds long to your project and drag on to the audioClip field.
|