o i @sNddlZddlZddlmZddlmZGdddZd dd Zd d d ZdS) N)hf_hub_download)KittenTTS_1_Onnxc@s:eZdZdZdddZdd d Zdd d ZeddZdS) KittenTTSz2Main KittenTTS class for text-to-speech synthesis.KittenML/kitten-tts-nano-0.8NcCs*d|vr d|}n|}t||d|_dS)zInitialize KittenTTS with a model from Hugging Face. Args: model_name: Hugging Face repository ID or model name cache_dir: Directory to cache downloaded files /z KittenML/repo_id cache_dirN)download_from_huggingfacemodel)self model_namer r rG/home/ubuntu/.local/lib/python3.10/site-packages/kittentts/get_model.py__init__ s zKittenTTS.__init__expr-voice-5-m?FcCs"td||jj||||dS)aGenerate audio from text. Args: text: Input text to synthesize voice: Voice to use for synthesis speed: Speech speed (1.0 = normal) Returns: Audio data as numpy array zGenerating audio for text: )voicespeed clean_text)printr generate)r textrrrrrrrs zKittenTTS.generate]cCs|jj|||||dS)a2Generate audio from text and save to file. Args: text: Input text to synthesize output_path: Path to save the audio file voice: Voice to use for synthesis speed: Speech speed (1.0 = normal) sample_rate: Audio sample rate )rr sample_rate)r generate_to_file)r r output_pathrrrrrrr(s zKittenTTS.generate_to_filecCs|jjS)zGet list of available voices.)r all_voice_names)r rrravailable_voices4szKittenTTS.available_voices)rN)rrF)rrr) __name__ __module__ __qualname____doc__rrrpropertyrrrrrrs    rKittenML/kitten-tts-nano-0.1cCst|d|d}t|d }t|}Wdn1swY|ddvr,tdt||d|d}t||d |d}t|||d i|d id }|S) zDownload model files from Hugging Face repository. Args: repo_id: Hugging Face repository ID cache_dir: Directory to cache downloaded files Returns: KittenTTS_1_Onnx: Instantiated model ready for use z config.json)r filenamer rNtype)ONNX1ONNX2zUnsupported model type. model_filevoices speed_priors voice_aliases) model_path voices_pathr-r.)ropenjsonloadget ValueErrorr)r r config_pathfconfigr/r0r rrrr :s,    r cCs t||S)zCGet a KittenTTS model (legacy function for backward compatibility).)rrrrr get_modeles r9)r%N) r2oshuggingface_hubr onnx_modelrrr r9rrrrs   3+