ML.PrepareAudioTokens¶
| Name | Mandatory | Description | Default | Type |
|---|---|---|---|---|
⬅️ Input |
The input of the shard, if any | String |
||
Output ➡️ |
The resulting output of the shard | [Int]Tensor |
||
Tokenizer |
No | The tokenizer to use. | none |
Var(Tokenizer) |
Language |
No | The language code (e.g. 'en', 'fr', etc). | none |
String |
Task |
No | The task type ('transcribe' or 'translate'). | none |
String |
Timestamps |
No | Whether to include timestamp tokens. | true |
Bool |
AsTensor |
No | Output as tensor instead of sequence. | false |
Bool |
GPU |
No | If true, the output tensor will be on GPU. | false |
Bool |
Prepares the initial tokens for Whisper audio processing with language and task settings.