Moved voices out of the tortoise folder because it kept being processed for setup.py

README.md

@@ -36,7 +36,7 @@ My fork boasts the following additions, fixes, and optimizations:
 * uses the entire audio sample instead of the first four seconds of each sound file for better reproducing
 * activated unused DDIM sampler
 * use of some optimizations like `kv_cache`ing for the autoregression sample pass, and keeping data on GPU 
-* compatability with DirectML
+* compatibilty with DirectML
 * easy install scripts
 * and more!
 
@@ -139,7 +139,9 @@ If you're looking to trim your clips, in my opinion, ~~Audacity~~ Tenacity works
 
 Power users with FFMPEG already installed can simply used the provided conversion script in `.\convert\`.
 
-After preparing your clips as WAV files at a sample rate of 22050 Hz, open up the `tortoise-tts` folder you're working in, navigate to `./tortoise/voice/`, create a new folder in whatever name you want, then dump your clips into that folder. While you're in the `voice` folder, you can take a look at the other provided voices.
+After preparing your clips as WAV files at a sample rate of 22050 Hz, open up the `tortoise-tts` folder you're working in, navigate to the `voices` folder, create a new folder in whatever name you want, then dump your clips into that folder. While you're in the `voice` folder, you can take a look at the other provided voices.
+
+**!**NOTE**!**: Before 2023.02.10, voices used to be stored under `.\tortoise\voices\`, but has been moved up one folder. Compatibily is maintained with the old voice folder, but will take priority.
 
 ## Using the Software
 
@@ -269,7 +271,7 @@ This was just a quick test for an adjustable setting, but this one turned out re
 To me, I find a few problems with TorToiSe over 11.AI:
 * computation time is quite an issue. Despite Stable Diffusion proving to be adequate on my 2060, TorToiSe takes quite some time with modest settings.
 	- However, on my 6800XT, performance was drastically uplifted due to having more VRAM for larger batch sizes (at the cost of Krashing).
-* reproducability in a voice depends on the "compatability" with the model TorToiSe was trained on.
+* reproducability in a voice depends on the "compatibilty" with the model TorToiSe was trained on.
 	- However, this also appears to be similar to 11.AI, where it was mostly trained on audiobook readings.
 * the lack of an obvious analog to the "stability" and "similarity" sliders kind of sucks, but it's not the end of the world.
 	However, the `temperature` option seems to prove to be a proper analog to either of these.

tortoise/utils/audio.py

@@ -10,8 +10,20 @@ from scipy.io.wavfile import read
 from tortoise.utils.stft import STFT
 
 
-BUILTIN_VOICES_DIR = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../voices')
+if 'TORTOISE_VOICES_DIR' not in os.environ:
+    voice_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../voices')
 
+    if not os.path.exists(voice_dir):
+        voice_dir = os.path.dirname('./voices/')
+    
+    os.environ['TORTOISE_VOICES_DIR'] = voice_dir
+
+BUILTIN_VOICES_DIR = os.environ.get('TORTOISE_VOICES_DIR')
+
+os.makedirs(BUILTIN_VOICES_DIR, exist_ok=True)
+
+def get_voice_dir():
+    return BUILTIN_VOICES_DIR
 
 def load_wav_to_torch(full_path):
     sampling_rate, data = read(full_path)

webui.py

@@ -17,7 +17,7 @@ from datetime import datetime
 from fastapi import FastAPI
 
 from tortoise.api import TextToSpeech
-from tortoise.utils.audio import load_audio, load_voice, load_voices
+from tortoise.utils.audio import load_audio, load_voice, load_voices, get_voice_dir
 from tortoise.utils.text import split_and_recombine_text
 
 args = None
@@ -75,7 +75,7 @@ def generate(
             conditioning_latents = (conditioning_latents[0], conditioning_latents[1], conditioning_latents[2], None)
             
         if voice != "microphone":
-            torch.save(conditioning_latents, f'./tortoise/voices/{voice}/cond_latents.pth')
+            torch.save(conditioning_latents, f'./{get_voice_dir()}/{voice}/cond_latents.pth')
         voice_samples = None
     else:
         sample_voice = None
@@ -235,7 +235,7 @@ def generate(
         f.write(json.dumps(info, indent='\t') )
 
     if voice is not None and conditioning_latents is not None:
-        with open(f'./tortoise/voices/{voice}/cond_latents.pth', 'rb') as f:
+        with open(f'./{get_voice_dir()}/{voice}/cond_latents.pth', 'rb') as f:
             info['latents'] = base64.b64encode(f.read()).decode("ascii")
 
     if args.embed_output_metadata:
@@ -297,7 +297,7 @@ def read_generate_settings(file, save_latents=True, save_as_temp=True):
         del j['latents']
 
     if latents and save_latents:
-        outdir=f'./tortoise/voices/{".temp" if save_as_temp else j["voice"]}/'
+        outdir=f'./{get_voice_dir()}/{".temp" if save_as_temp else j["voice"]}/'
         os.makedirs(outdir, exist_ok=True)
         with open(f'{outdir}/cond_latents.pth', 'wb') as f:
             f.write(latents)
@@ -390,7 +390,7 @@ def reload_tts():
     tts = setup_tortoise()
 
 def update_voices():
-    return gr.Dropdown.update(choices=sorted(os.listdir("./tortoise/voices")) + ["microphone"])
+    return gr.Dropdown.update(choices=sorted(os.listdir(get_voice_dir())) + ["microphone"])
 
 def export_exec_settings( share, listen, check_for_updates, models_from_local_only, low_vram, embed_output_metadata, latents_lean_and_mean, cond_latent_max_chunk_size, sample_batch_size, concurrency_count, output_sample_rate, output_volume ):
     args.share = share
@@ -517,7 +517,7 @@ def setup_gradio():
                     )
                     prompt = gr.Textbox(lines=1, label="Custom Emotion + Prompt (if selected)")
                     voice = gr.Dropdown(
-                        sorted(os.listdir("./tortoise/voices")) + ["microphone"],
+                        sorted(os.listdir(get_voice_dir())) + ["microphone"],
                         label="Voice",
                         type="value",
                     )