daekeun-ml commited on
Commit
a28266d
ยท
verified ยท
1 Parent(s): 67c143c
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -149,6 +149,9 @@ response = processor.batch_decode(
149
  print(response) # "๋ชฌํ†  ํ‚ฌ์€ ์ž๋…€๋“ค์ด ์‚ฌ๋ž‘์„ ์ œ๋Œ€๋กœ ๋ชป ๋ฐ›๊ณ  ํฌ๋ฉด ๋งค์šฐ ์‹ฌ๊ฐํ•œ ๊ฒฐ๊ณผ๊ฐ€ ์ดˆ๋ž˜๋œ๋‹ค๋Š” ๊ฒฐ๋ก ์„ ๋‚ด๋ ธ์Šต๋‹ˆ๋‹ค"
150
  ```
151
 
 
 
 
152
  ## References
153
 
154
  - https://huggingface.co/microsoft/Phi-4-multimodal-instruct
 
149
  print(response) # "๋ชฌํ†  ํ‚ฌ์€ ์ž๋…€๋“ค์ด ์‚ฌ๋ž‘์„ ์ œ๋Œ€๋กœ ๋ชป ๋ฐ›๊ณ  ํฌ๋ฉด ๋งค์šฐ ์‹ฌ๊ฐํ•œ ๊ฒฐ๊ณผ๊ฐ€ ์ดˆ๋ž˜๋œ๋‹ค๋Š” ๊ฒฐ๋ก ์„ ๋‚ด๋ ธ์Šต๋‹ˆ๋‹ค"
150
  ```
151
 
152
+ ### Demos
153
+ Please refer to the Jupyter notebook and video clips in the [demo folder](https://huggingface.co/daekeun-ml/Phi-4-multimodal-finetune-ko-speech/tree/main/demos). They are not production-quality as they were simply fine-tuned for PoC purposes, but you can see that they transcribe and translate with high accuracy even when a native speaker speaks quite quickly.
154
+
155
  ## References
156
 
157
  - https://huggingface.co/microsoft/Phi-4-multimodal-instruct