iOS_Android_SDK
Collection
Bunch of models for deployment on iOS and macOS devices โข 40 items โข Updated
How to use TheStageAI/pocket-tts-100m-tr with Pocket-TTS:
from pocket_tts import TTSModel
import scipy.io.wavfile
tts_model = TTSModel.load_model("TheStageAI/pocket-tts-100m-tr")
voice_state = tts_model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)
audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.")
# Audio is a 1D torch tensor containing PCM data.
scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy())Core ML / ANE engines of the Turkish 100M-parameter Pocket TTS fine-tune
wite-tech/pocket-tts-turkish by wite-tech (CC-BY-4.0; six synthetic voices by the author),
built on kyutai/pocket-tts, for the TheStage Apple SDK
(model_type: pocket-tts, bundle language tr).
subscription/macos_ios/engines.zip (151 MB) โ flow LM fp16 with 6-bit g8 palettized transformer layers
(6 layers, d=1024, LSD flow head, ANE), Mimi decoder fp32 (CPU), voices: female_1 (default, the author's reference voice), female_2, female_3, male_1, male_2, male_3, plus the English references azelma, alba, charles, cosette, javert, marius. QLPA-encrypted engines.