Commit comparisons with naturalspeech

This is the first TTS engine I've seen come along that has comparable performance
to Tortoise, though what has been released is pretty sparse on actual results. Still,
it's an interesting comparison.

tortoise_v2_examples.html

@@ -32,10 +32,10 @@ available at <a href="https://github.com/neonbjb/tortoise-tts">https://github.co
 <h2>Short-form</h2>
 <audio controls="" style="width: 600px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/favorite_riding_hood.mp3" type="audio/mp3"></audio><br>
 
-<h1>Compared to Tacotron2 (with the LJSpeech voice): 🐢 </h1>
+<h1>Comparisons (with the LJSpeech voice): 🐢 </h1>
 <p>LJSpeech is a popular dataset used to train small-scale TTS models. TorToiSe is a multi-voice model, following is how
-it renders the LJSpeech voice with no fine-tuning, compared with results for the same text from the popular Tacotron2
-model paired with the Waveglow transformer:</p>
+it renders the LJSpeech voice with and without fine-tuning, compared with results for the same text from the popular Tacotron2
+model paired with the Waveglow vocoder.</p>
 <table><th>Tacotron2+Waveglow</th><th>TorToiSe</th><th>TorToiSe Finetuned</th><tr>
     <td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/tacotron_comparison/2-tacotron2.mp3" type="audio/mp3"></audio><br>
 </td>
@@ -50,6 +50,22 @@ model paired with the Waveglow transformer:</p>
 
     <td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/finetuned/lj/4.mp3" type="audio/mp3"></audio><br></td>
 </tr></table>
+<p>NaturalVoice is a SOTA TTS engine developed by Microsoft Research Asia in May 2022. It features realistic prosody
+and end-to-end generation with no need for a vocoder. While not much has actually been released about this model other
+than five samples, those samples are quite good and I would consider this the most competitive TTS engine out there
+right now.</p>
+<table><th>Natural Voice</th><th>TorToiSe Finetuned</th>
+<tr><td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/naturalspeech_comparison/lax/naturalspeech.mp3" type="audio/mp3"></audio><br></td>
+<td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/naturalspeech_comparison/lax/tortoise.mp3" type="audio/mp3"></audio><br></td>
+</tr><tr><td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/naturalspeech_comparison/maltby/naturalspeech.mp3" type="audio/mp3"></audio><br></td>
+<td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/naturalspeech_comparison/maltby/tortoise.mp3" type="audio/mp3"></audio><br></td>
+</tr><tr><td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/naturalspeech_comparison/fibers/naturalspeech.mp3" type="audio/mp3"></audio><br>
+</td><td><audio controls="" style="width: 300px;"><source src="https://github.com/neonbjb/tortoise-tts/raw/main/examples/naturalspeech_comparison/fibers/tortoise.mp3" type="audio/mp3"></audio><br></td>
+</tr></table>
+<p>It is important to note that it is not actually fair to compare any of these models: Tortoise is a multi-voice probabilistic
+model trained on millions of hours of speech with an exceptionally slow inference time. Tacotron and NaturalVoice are efficient,
+fast, single-voice models trained on 24 hours of speech. Unfortunately, there isn't much in the way of actually comparable
+research to Tortoise.</p>
 
 <h1>All Results 🐢</h1>
 <p>    Following are all the results from which the hand-picked results were drawn from. Also included is the reference