Instructions to use reiscook/pocket-tts-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use reiscook/pocket-tts-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download reiscook/pocket-tts-mlx --local-dir pocket-tts-mlx
- Pocket-TTS
How to use reiscook/pocket-tts-mlx with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("reiscook/pocket-tts-mlx") 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
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload int4/tokenizer_config.json with huggingface_hub
Browse files
int4/tokenizer_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "T5Tokenizer",
|
| 3 |
+
"model_max_length": 512
|
| 4 |
+
}
|