Set speaking speed (length_scale): male 1.43, female 1.11

README.md

@@ -78,6 +78,19 @@ The Tamil-script and Sourashtra-script models produce speech from the same speak
 
 ---
 
+## Speaking Speed
+
+Each `config.json` sets `model_args.length_scale`, which controls speaking speed (higher = slower):
+
+| Speaker | `length_scale` |
+|---------|----------------|
+| Male | 1.43 |
+| Female | 1.11 |
+
+At the default of 1.0 the male models speak too fast (about 1/0.7 of natural speed) and the female models slightly fast (about 1/0.9). To change the speed, edit `length_scale` in the model's `config.json`.
+
+---
+
 ## Training
 
 | Parameter | Value |

Sourashtra-Female_Script-sourashtra/config.json

@@ -127,7 +127,7 @@
         "use_sdp": true,
         "noise_scale": 1.0,
         "inference_noise_scale": 0.667,
-        "length_scale": 1,
+        "length_scale": 1.11,
         "noise_scale_dp": 1.0,
         "inference_noise_scale_dp": 1.0,
         "max_inference_len": null,

Sourashtra-Female_Script-tamil/config.json

@@ -127,7 +127,7 @@
         "use_sdp": true,
         "noise_scale": 1.0,
         "inference_noise_scale": 0.667,
-        "length_scale": 1,
+        "length_scale": 1.11,
         "noise_scale_dp": 1.0,
         "inference_noise_scale_dp": 1.0,
         "max_inference_len": null,

Sourashtra-Male_Script-sourashtra/config.json

@@ -127,7 +127,7 @@
         "use_sdp": true,
         "noise_scale": 1.0,
         "inference_noise_scale": 0.667,
-        "length_scale": 1,
+        "length_scale": 1.43,
         "noise_scale_dp": 1.0,
         "inference_noise_scale_dp": 1.0,
         "max_inference_len": null,

Sourashtra-Male_Script-tamil/config.json

@@ -127,7 +127,7 @@
         "use_sdp": true,
         "noise_scale": 1.0,
         "inference_noise_scale": 0.667,
-        "length_scale": 1,
+        "length_scale": 1.43,
         "noise_scale_dp": 1.0,
         "inference_noise_scale_dp": 1.0,
         "max_inference_len": null,