MoshiDepthLayout
Enums · AiDotNet.TextToSpeech.MultiModal
Which audio streams Moshi’s Depth Transformer predicts.
Fields
| Field | Summary |
|---|---|
MoshiDepthLayout AllStreams |
The paper’s (Eq. |
MoshiDepthLayout MoshiStreams |
The release’s (dep_q = 8, kyutai/moshiko and moshika): Moshi’s Q audio streams; the user’s are input only. |
int value__ |