Update README.md
Browse files
README.md
CHANGED
|
@@ -17,4 +17,8 @@ This is the [Whisper Tiny](https://huggingface.co/openai/whisper-tiny) model tes
|
|
| 17 |
* **IMPORTANT:** The audio must be 16kHz. In the audio inspector select "Force Mono". And "Decompress on Load".
|
| 18 |
* You can add a step to convert 44kHz or 22kHz audio to 16kHz with [this model](https://huggingface.co/unity/sentis-audio-frequency-to-16khz)
|
| 19 |
|
| 20 |
-
When you press play the transcription of the audio will be displayed in the console window.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
* **IMPORTANT:** The audio must be 16kHz. In the audio inspector select "Force Mono". And "Decompress on Load".
|
| 18 |
* You can add a step to convert 44kHz or 22kHz audio to 16kHz with [this model](https://huggingface.co/unity/sentis-audio-frequency-to-16khz)
|
| 19 |
|
| 20 |
+
When you press play the transcription of the audio will be displayed in the console window.
|
| 21 |
+
|
| 22 |
+
## Languages
|
| 23 |
+
The output starts with 4 tokens which you can set. One token specifies the input language. One token specifies whether it is straight transcription into the specified language or if it is translated to English. See [here](https://huggingface.co/openai/whisper-tiny) for more details.
|
| 24 |
+
These special tokens are defined in the added_tokens.json file.
|