0.10.0

config/pre_process_map.default.yaml

@@ -0,0 +1,39 @@
+# regex pairs to clean the text before speaking
+- - ([^.])\.$
+  - \1
+- - '&'
+  - '&'
+- - '<'
+  - <
+- - '&gt;'
+  - '>'
+- - '&quot;'
+  - '"'
+- - '&#x27;'
+  - ''''
+- - '&copy;'
+  - '©'
+- - '&reg;'
+  - '®'
+- - '&nbsp;'
+  - ' '
+- - '"'
+  - ''
+- - ' biases '
+  - ' bias''s '
+- - ex\.
+  - for example
+- - e\.g\.
+  - for example
+- - ' ESG '
+  - ' E.S.G. '
+- - ' FY '
+  - ' F.Y. '
+- - ([0-9]+)-([0-9]+)
+  - \1 to \2
+- - '[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F700-\U0001F77F\U0001F780-\U0001F7FF\U0001F800-\U0001F8FF\U0001F900-\U0001F9FF\U0001FA00-\U0001FA6F\U0001FA70-\U0001FAFF\U00002702-\U000027B0\U000024C2-\U0001F251]+'
+  - ''
+- - '\*\*\*'
+  - '*'
+- - '\*\*'
+  - '*'

config/voice_to_speaker.default.yaml

@@ -0,0 +1,56 @@
+tts-1:
+  some_other_voice_name_you_want:
+    model: voices/choose your own model.onnx
+    speaker: set your own speaker
+  alloy:
+    model: voices/en_US-libritts_r-medium.onnx
+    speaker: 79 # 64, 79, 80, 101, 130
+  echo:
+    model: voices/en_US-libritts_r-medium.onnx
+    speaker: 134 # 52, 102, 134
+  echo-alt:
+    model: voices/en_US-ryan-high.onnx
+    speaker: # default speaker
+  fable:
+    model: voices/en_GB-northern_english_male-medium.onnx
+    speaker: # default speaker
+  onyx:
+    model: voices/en_US-libritts_r-medium.onnx
+    speaker: 159 # 55, 90, 132, 136, 137, 159
+  nova:
+    model: voices/en_US-libritts_r-medium.onnx
+    speaker: 107 # 57, 61, 107, 150, 162
+  shimmer:
+    model: voices/en_US-libritts_r-medium.onnx
+    speaker: 163
+tts-1-hd:
+  alloy:
+    model: xtts
+    speaker: voices/alloy-alt.wav
+  alloy-orig: 
+    model: xtts
+    speaker: voices/alloy.wav # it's REALLY BAD
+  echo:
+    model: xtts
+    speaker: voices/echo.wav
+  fable:
+    model: xtts
+    speaker: voices/fable.wav
+  onyx:
+    model: xtts
+    speaker: voices/onyx.wav
+  nova:
+    model: xtts
+    speaker: voices/nova.wav
+  shimmer:
+    model: xtts
+    speaker: voices/shimmer.wav
+  me:
+    model: xtts_v2.0.2 # you can specify different xtts version
+    speaker: voices/me.wav # this could be you
+  parler:
+    model: parler-tts/parler_tts_mini_v0.1
+    speaker: A female speaker with a slightly low-pitched voice delivers her words quite expressively, in a very confined sounding environment with clear audio quality. She speaks very fast.
+  parler2:
+    model: parler-tts/parler_tts_mini_v0.1
+    speaker: A female voice with an Indian accent enunciates every word with precision. The speaker's voice is very close-sounding, and the recording is excellent, capturing her voice with crisp clarity.