GitHub
184.3K
Download
Models
Docs
Pricing
Sign in
Download
Models
Docs
Pricing
Sign in
phonon
:fr
65
Downloads
Updated
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.
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.
Cancel
phonon:fr
...
/
json
1ba08d75f0ab · 747B
{
"audio_tokenizer": {
"audio_tokenizer_class": "PocketTTSAudioTokenizerModel",
"audio_tokenizer_name_or_path": "gradium/phonon-mimi"
},
"fade_in_duration": 0.0,
"feature_extractor": {
"analysis_frame_duration": 0.02,
"end_on_pause": true,
"fade_out_duration": 0.02,
"feature_extractor_type": "PocketTTSFeatureExtractor",
"feature_size": 1,
"frame_size": 1920,
"pad_to_multiple_of": 1920,
"padding_side": "right",
"padding_value": 0.0,
"pause_duration": 0.08,
"return_attention_mask": true,
"sampling_rate": 24000,
"silence_floor_db": 35.0
},
"frames_after_eos": 1,
"frames_after_eos_short_text": 3,
"processor_class": "PocketTTSProcessor",
"short_text_max_words": 4
}