Update README.md

README.md

@@ -90,11 +90,7 @@ Measured using Sarvam-1 (2B) on Whisper-v3 transcriptions of generated speech.
 
 ### Human Evaluation
 
-63 evaluators completed 2,125 rating tasks comparing human speech with model responses. Each instance contained two audio samples (Voice A: Human, Voice B: Model) rated on 5-point Likert scales for naturalness and clarity.
-
-| Dataset | Ratings | Female | Male | 18–25 | 25–30 | 30–35 |
-|---|---|---|---|---|---|---|
-| Speech Dialogue Eval. | 2,125 | 34 | 29 | 28 | 19 | 8 |
+130 evaluators completed 2,125 rating tasks comparing human speech with model responses. Each instance contained two audio samples (Voice A: Human, Voice B: Model) rated on 5-point Likert scales for naturalness and clarity.
 
 **Perceptual quality:**