Change default voice for Kokoro TTS to af_gladiatrix

`af_gladiatrix` is the new default voice for Kokoro TTS. It is the equally weighted mean of all other American female voices (except `af_nicole`, who is an ASMR exception):
- af_0
- af_alloy
- af_bella
- af_jessica
- af_nova
- af_river
- af_sarah
- af_sky

This helps address some of the "overfitting to one voice" concerns raised in [closed PR #14](https://huggingface.co/spaces/Pendrokar/TTS-Spaces-Arena/discussions/14), without the downsides of stochasticity. Also, `af_gladiatrix` could simply be a better voice than its predecessor `af_0`.

TODO for

@Pendrokar

if this PR is accepted: purge and refresh cached samples. Let me know if you need my help with this.

Matching commit: https://huggingface.co/spaces/hexgrad/Kokoro-TTS/commit/1daab5c11c6981ae05062909f04ceebb23e0609b

app.py

@@ -448,7 +448,7 @@ OVERRIDE_INPUTS = {
 
     # StyleTTS 2 kokoro
     'hexgrad/kokoro': {
-		1: "af_0", #voice
+		1: "af_gladiatrix", #voice
 		2: None, #ps
 		3: 1, #speed
 		4: 0.5, #reduce_noise