Added code to generate the default voices (#144)

scripts/generate_default_voices.py

@@ -0,0 +1,23 @@
+import scipy.io.wavfile
+
+from pocket_tts import TTSModel, export_model_state
+from pocket_tts.utils.utils import _ORIGINS_OF_PREDEFINED_VOICES
+
+model = TTSModel.load_model()
+
+for voice_name, voice_origin in _ORIGINS_OF_PREDEFINED_VOICES.items():
+    print(f"Processing voice: {voice_name} from origin: {voice_origin}")
+    # Export a voice state for fast loading later
+    model_state = model.get_state_for_audio_prompt(voice_origin)
+    export_model_state(model_state, f"./built-in-voices/{voice_name}.safetensors")
+
+    model_state_copy = model.get_state_for_audio_prompt(
+        f"./built-in-voices/{voice_name}.safetensors"
+    )
+
+    audio = model.generate_audio(
+        model_state_copy, "Hello, it's a good day, isn't it? I hope you are doing well."
+    )
+    scipy.io.wavfile.write(
+        f"./built-in-voices-generated/{voice_name}.wav", model.sample_rate, audio.numpy()
+    )

scripts/generate_default_voices.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-set -ex
-# Generate safetensors files for all default voices
-
-OUTPUT_DIR="${1:-./default_voices}"
-mkdir -p "$OUTPUT_DIR"
-
-# Default voices with their Hugging Face paths
-# The marius voice can benefit from a bit of cleaning
-declare -A voices=(
-    ["alba"]="hf://kyutai/tts-voices/alba-mackenna/casual.wav"
-    ["marius"]="hf://kyutai/tts-voices/voice-donations/Selfie.wav"
-    ["javert"]="hf://kyutai/tts-voices/voice-donations/Butter.wav"
-    ["jean"]="hf://kyutai/tts-voices/ears/p010/freeform_speech_01.wav"
-    ["fantine"]="hf://kyutai/tts-voices/vctk/p244_023.wav"
-    ["cosette"]="hf://kyutai/tts-voices/expresso/ex04-ex02_confused_001_channel1_499s.wav"
-    ["eponine"]="hf://kyutai/tts-voices/vctk/p262_023.wav"
-    ["azelma"]="hf://kyutai/tts-voices/vctk/p303_023.wav"
-)
-
-for voice in "${!voices[@]}"; do
-    echo "Exporting voice: $voice"
-    uv run pocket-tts export-voice "${voices[$voice]}" "$OUTPUT_DIR/$voice.safetensors"
-done
-
-echo "Done! Voice files saved to $OUTPUT_DIR"