High-Quality Voice Cloning TTS for 600+ Languages
Python
set load_asr=True in colab notebook
Han Zhuf7f5040646f4
diff --git a/docs/OmniVoice.ipynb b/docs/OmniVoice.ipynbindex 0d2234e..b440f31 100644--- a/docs/OmniVoice.ipynb+++ b/docs/OmniVoice.ipynb@@ -47,18 +47,7 @@"execution_count": null,"metadata": {},"outputs": [],- "source": [- "from omnivoice import OmniVoice\n",- "import soundfile as sf\n",- "import torch\n",- "from IPython.display import Audio, display\n",- "\n",- "model = OmniVoice.from_pretrained(\n",- " \"k2-fsa/OmniVoice\",\n",- " device_map=\"cuda:0\",\n",- " dtype=torch.float16,\n",- ")"- ]+ "source": "from omnivoice import OmniVoice\nimport soundfile as sf\nimport torch\nfrom IPython.display import Audio, display\n\nmodel = OmniVoice.from_pretrained(\n \"k2-fsa/OmniVoice\",\n device_map=\"cuda:0\",\n dtype=torch.float16,\n load_asr=True,\n)"},{"cell_type": "markdown",