phonon:es

65 4 hours ago

Phonon is Gradium’s text-to-speech family. It turns written text into spoken audio as it generates, making it useful for reading assistant replies, narrating passages, and adding a voice to local apps.

... /
json
17d12cf8dee2 · 575B
{
"tokenizer_class": "TokenizersBackend",
"fast_tokenizer_files": [
"tokenizer.5.0.0.json"
],
"unk_token": "\u0000<unk>",
"bos_token": "\u0000<s>",
"eos_token": "\u0000</s>",
"pad_token": "\u0000<pad>",
"padding": true,
"padding_side": "left",
"return_tensors": "pt",
"model_input_names": [
"input_ids",
"attention_mask"
],
"clean_up_tokenization_spaces": false,
"model_specific_special_tokens": {
"audio_prompt_token": "<|audio_prompt|>",
"audio_latent_token": "<|audio_latent|>",
"audio_bos_token": "<|audio_bos|>"
}
}