Only english voices are loaded. Support for other languages might com…

…e later
h43lb1t0 · Feb 2, 2025 · e7503f2 · e7503f2
1 parent 849d355
commit e7503f2
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -10,6 +10,9 @@ Enhance your text generation experience with the Kokoro TTS extension, seamlessl
 
 ## Features
 
+**Current Version:** Kokoro v1
+**Supported Languages:** English
+
 Kokoro TTS is limited to inputs up to **510 tokens**. *Note that Kokoro tokens differ from LLM tokens.* This extension allows you to generate longer audio outputs by splitting the input text into segments and concatenating the resulting audio.
 
 ### Text Splitting Methods
@@ -65,6 +68,7 @@ By default, the extension utilizes the first available GPU. To specify a differe
 - [x] Kokoro v1
 - [x] Support for all operating systems
 - [x] Voice selection feature
+- [ ] Support for other languages than English
 - [ ] Support for future versions of Kokoro
 
 ## Contributing

diff --git a/src/kokoro.py b/src/kokoro.py
@@ -72,6 +72,7 @@ def normalize_text(text):
     return text.strip()
 
 def get_vocab():
+    # Probably needs updates starting here to support other languages
     _pad = "$"
     _punctuation = ';:,.!?¡¿—…"«»“” '
     _letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'

diff --git a/src/voices.py b/src/voices.py
@@ -5,3 +5,6 @@
 snapshot_path = snapshot_path / os.listdir(snapshot_path)[0]
 voices = os.listdir(snapshot_path / 'voices')
 VOICES = [voice.replace('.pt', '') for voice in voices]
+
+# Filter the voices to only english voices
+VOICES = [voice for voice in VOICES if voice.startswith(('a', 'b'))]