Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ Ultravox is a multimodal Speech LLM built around a pretrained Whisper and Llama
15
  ### Model Description
16
 
17
  Ultravox is a multimodal model that can consume both speech and text as input (e.g., a text system prompt and voice user message).
18
- The input to the model is given as a text prompt with a special <|audio|> token, and the model processor will replace this magic token with embeddings derived from the input audio.
19
  Using the merged embeddings as input, the model will then generate output text as usual.
20
 
21
  In a future revision of Ultravox, we plan to expand the token vocabulary to support generation of semantic and acoustic audio tokens, which can then be fed to a vocoder to produce voice output.
 
15
  ### Model Description
16
 
17
  Ultravox is a multimodal model that can consume both speech and text as input (e.g., a text system prompt and voice user message).
18
+ The input to the model is given as a text prompt with a special <|audio|> pseudo-token, and the model processor will replace this magic token with embeddings derived from the input audio.
19
  Using the merged embeddings as input, the model will then generate output text as usual.
20
 
21
  In a future revision of Ultravox, we plan to expand the token vocabulary to support generation of semantic and acoustic audio tokens, which can then be fed to a vocoder to produce voice output.