Hugging Face's logo

Spaces:
adi-123
/
Image-to-Audio_Story_Generator
Running

App Files Community
adi-123 commited on
Commit
83e3bd6
·
1 Parent(s): f2710b4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -25,7 +25,7 @@ The goal of this project is to leverage AI capabilities to convert an uploaded i
25
  - Utilizes Salesforce's `blip-image-captioning-base` model to generate textual descriptions of uploaded images.
26
 
27
  ### ✍️ Text Generation (Story Creation)
28
- - Employs OpenAI's `togethercomputer/llama-2-70b-chat` model to create a short story influenced by the provided image caption within a positive conclusion of 100 words or less.
29
 
30
  ### 🔊 Text-to-Speech Conversion
31
  - Utilizes Hugging Face's `espnet/kan-bayashi_ljspeech_vits` model to convert the generated story into an audio file.
 
25
  - Utilizes Salesforce's `blip-image-captioning-base` model to generate textual descriptions of uploaded images.
26
 
27
  ### ✍️ Text Generation (Story Creation)
28
+ - Employs Meta's `llama-2-70b-chat` model to create a short story influenced by the provided image caption within a positive conclusion of 100 words or less.
29
 
30
  ### 🔊 Text-to-Speech Conversion
31
  - Utilizes Hugging Face's `espnet/kan-bayashi_ljspeech_vits` model to convert the generated story into an audio file.