Interface: SpeechToTextModelConfig

Defined in: types/stt.ts:270

Configuration for Speech to Text model.

Properties

isMultilingual

isMultilingual: boolean

Defined in: types/stt.ts:280

A boolean flag indicating whether the model supports multiple languages.

---

modelName

modelName: SpeechToTextModelName

Defined in: types/stt.ts:275

The built-in model name (e.g. 'whisper-tiny-en'). Used for telemetry and hook reload triggers. Pass one of the pre-built STT constants (e.g. WHISPER_TINY_EN) to populate all required fields.

---

modelSource

modelSource: ResourceSource

Defined in: types/stt.ts:287

A string that specifies the location of a .pte file for the model.

We expect the model to have 2 bundled methods: 'decode' and 'encode'.

---

tokenizerSource

tokenizerSource: ResourceSource

Defined in: types/stt.ts:292

A string that specifies the location to the tokenizer for the model.