From 2a5166d9e1a24c122fe71ccaf868f1bcab014e5c Mon Sep 17 00:00:00 2001
From: James Betker <jbetker@gmail.com>
Date: Mon, 25 Apr 2022 20:05:21 -0600
Subject: [PATCH] add regenerate option

---
 README.md | 8 ++++++++
 read.py   | 7 +++++++
 2 files changed, 15 insertions(+)

diff --git a/README.md b/README.md
index 4627f62..bd696f2 100644
--- a/README.md
+++ b/README.md
@@ -44,10 +44,18 @@ python do_tts.py --text "I'm going to speak this" --voice dotrice --preset fast
 ### read.py
 
 This script provides tools for reading large amounts of text.
+
 ```shell
 python read.py --textfile <your text to be read> --voice dotrice
 ```
 
+This will break up the textfile into sentences, and then convert them to speech one at a time. It will output a series 
+of spoken clips as they are generated. Once all the clips are generated, it will combine them into a single file and
+output that as well.
+
+Sometimes Tortoise screws up an output. You can re-generate any bad clips by re-running `read.py` with the --regenerate
+argument.
+
 ### API
 
 Tortoise can be used programmatically, like so:
diff --git a/read.py b/read.py
index 04cd7a0..9506e97 100644
--- a/read.py
+++ b/read.py
@@ -35,6 +35,7 @@ if __name__ == '__main__':
                                                  'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='patrick_stewart')
     parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/longform/')
     parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='standard')
+    parser.add_argument('--regenerate', type=str, help='Comma-separated list of clip numbers to re-generate, or nothing.', default=None)
     parser.add_argument('--voice_diversity_intelligibility_slider', type=float,
                         help='How to balance vocal diversity with the quality/intelligibility of the spoken text. 0 means highly diverse voice (not recommended), 1 means maximize intellibility',
                         default=.5)
@@ -43,6 +44,9 @@ if __name__ == '__main__':
     outpath = args.output_path
     voices = get_voices()
     selected_voices = args.voice.split(',')
+    regenerate = args.regenerate
+    if regenerate is not None:
+        regenerate = [int(e) for e in regenerate.split(',')]
     for selected_voice in selected_voices:
         voice_outpath = os.path.join(outpath, selected_voice)
         os.makedirs(voice_outpath, exist_ok=True)
@@ -71,6 +75,9 @@ if __name__ == '__main__':
             conds.append(c)
         all_parts = []
         for j, text in enumerate(texts):
+            if regenerate is not None and j not in regenerate:
+                all_parts.append(load_audio(os.path.join(voice_outpath, f'{j}.wav'), 24000))
+                continue
             gen = tts.tts_with_preset(text, conds, preset=args.preset, clvp_cvvp_slider=args.voice_diversity_intelligibility_slider)
             gen = gen.squeeze(0).cpu()
             torchaudio.save(os.path.join(voice_outpath, f'{j}.wav'), gen, 24000)