Instructions to use borisbat/dasllama-tts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KittenTTS
How to use borisbat/dasllama-tts with KittenTTS:
from kittentts import KittenTTS m = KittenTTS("borisbat/dasllama-tts") audio = m.generate("This high quality TTS model works without a GPU") # Save the audio import soundfile as sf sf.write('output.wav', audio, 24000) - Pocket-TTS
How to use borisbat/dasllama-tts with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("borisbat/dasllama-tts") 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()) - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- 2.15 kB
- 11.4 kB
- 18.7 kB
- 1.81 kB
- 1.02 kB
- 1.13 kB
- 1.08 kB
- 20 kB
- 10.6 kB
- 296 MB xet
- 252 Bytes
- 59.3 MB xet
- 252 Bytes
- 353 MB xet
- 253 Bytes
- 137 MB xet
- 618 Bytes
- 77.8 MB xet
- 2.29 kB
- 137 MB xet
- 2.25 kB
- 67 MB xet
- 808 Bytes
- 137 MB xet
- 630 Bytes
- 377 MB xet
- 656 Bytes
- 137 MB xet
- 634 Bytes
- 137 MB xet
- 635 Bytes
- 14 MB xet
- 365 Bytes
- 10.3 MB xet
- 339 Bytes
- 12.6 MB xet
- 390 Bytes