Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

	@@ -46,6 +46,8 @@ To highlight the relationship between pitch and rotary embeddings echo implement
46
47
48


49	By modulating the RoPE frequencies based on pitch (F0), we are essentially telling the model to pay attention to the acoustic features relate to sequence position in a way that's proportional to the voice characteristics. This approach creates a more speech-aware positional representation that helps the model better understand the relationship between acoustic features and text.
50
51


46
47
48
49	+ Whisper: STEP 1000 • WER:91.89% • Loss:7.8292 • LR:0.00098035
50	+
51	By modulating the RoPE frequencies based on pitch (F0), we are essentially telling the model to pay attention to the acoustic features relate to sequence position in a way that's proportional to the voice characteristics. This approach creates a more speech-aware positional representation that helps the model better understand the relationship between acoustic features and text.
52
53