Instructions to use MacEpic/pocket-tts-de-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use MacEpic/pocket-tts-de-coreml with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("MacEpic/pocket-tts-de-coreml") 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
Download bundle.json from MacEpic/pocket-tts-de-coreml: direct link, hf CLI and curl.
- Browser
- Download file 3.45 kB
-
https://huggingface.co/MacEpic/pocket-tts-de-coreml/resolve/main/bundle.json
- Command line
-
hf download hf://MacEpic/pocket-tts-de-coreml/bundle.json
-
curl -L -o bundle.json https://huggingface.co/MacEpic/pocket-tts-de-coreml/resolve/main/bundle.json
3.45 kB
| { | |
| "built": 1794179327, | |
| "conditions": {}, | |
| "ctx": 415, | |
| "dims": { | |
| "attn": 1024, | |
| "d": 1024, | |
| "ff": 4096, | |
| "flow_blocks": 6, | |
| "flow_d": 512, | |
| "heads": 16, | |
| "kv_heads": 16, | |
| "layers": 6, | |
| "ldim": 32, | |
| "z": null | |
| }, | |
| "eos_threshold": -4.0, | |
| "files": [ | |
| { | |
| "path": "flow-c415-t1.mlpackage/Data/com.apple.CoreML/model.mlmodel", | |
| "sha256": "0d5375dad37c7c8c0e6f251beb8f3487362db29a64a3a64dc5cb1cf01ec500c7", | |
| "size": 323041 | |
| }, | |
| { | |
| "path": "flow-c415-t1.mlpackage/Data/com.apple.CoreML/weights/weight.bin", | |
| "sha256": "f56e817df74a348408e1a4ef30684ff16777161337122af95a3a2c800acc89ce", | |
| "size": 168889280 | |
| }, | |
| { | |
| "path": "flow-c415-t1.mlpackage/Manifest.json", | |
| "sha256": "ea22c6a8170df019c2b09e0663db6c35b01917db9692261f8ca8a6118925f4c6", | |
| "size": 534 | |
| }, | |
| { | |
| "path": "flow-c415-t48.mlpackage/Data/com.apple.CoreML/model.mlmodel", | |
| "sha256": "06117a1610e340f8bc8b8af5a7763c71852d0b74a5e77e4d88b528ca00b17f0b", | |
| "size": 323041 | |
| }, | |
| { | |
| "path": "flow-c415-t48.mlpackage/Data/com.apple.CoreML/weights/weight.bin", | |
| "sha256": "f56e817df74a348408e1a4ef30684ff16777161337122af95a3a2c800acc89ce", | |
| "size": 168889280 | |
| }, | |
| { | |
| "path": "flow-c415-t48.mlpackage/Manifest.json", | |
| "sha256": "7b525f916d9fa724e5dfcf5464ae0a387eb8b3391047ef4063af8ec5afce26f5", | |
| "size": 534 | |
| }, | |
| { | |
| "path": "host.safetensors", | |
| "sha256": "cbaab2aca26db4c8af928e2316c08027fe02f096d575a572e39f3e9013fb45c5", | |
| "size": 16523760 | |
| }, | |
| { | |
| "path": "mimi-c266.mlpackage/Data/com.apple.CoreML/model.mlmodel", | |
| "sha256": "d317be723cc7f6eda07399d7496e445faebc4bb9724f79e913fc7059a1b63930", | |
| "size": 131135 | |
| }, | |
| { | |
| "path": "mimi-c266.mlpackage/Data/com.apple.CoreML/weights/weight.bin", | |
| "sha256": "2e7d230184aa1bc8b1426cdecf814a408726887fa84aa05e3b54defc87db9c35", | |
| "size": 41182464 | |
| }, | |
| { | |
| "path": "mimi-c266.mlpackage/Manifest.json", | |
| "sha256": "07ab3ba0cae8d2a9b96a67d04128c6ae8f2236d8f2dd9f8da261d1d1aaa5d2bb", | |
| "size": 534 | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "sha256": "2d77849811e3d1b6ae80e5b11b203f57e1847901104d8a0573b34f46f8dddb53", | |
| "size": 245966 | |
| }, | |
| { | |
| "path": "voices/alba.safetensors", | |
| "sha256": "d04800af8b32264300eb7d03cacb08ae7e88fd341df9f81f9784f10de27f9114", | |
| "size": 516176 | |
| }, | |
| { | |
| "path": "voices/anna.safetensors", | |
| "sha256": "14be25af1023b537435ed5baed788c10818018e828cc9caee9e5af177aacd832", | |
| "size": 516176 | |
| }, | |
| { | |
| "path": "voices/bill.safetensors", | |
| "sha256": "ab60c757f20e520a37e84bc2a5991617bdc31928a9c6d5f17fe6348bd0c7e909", | |
| "size": 516176 | |
| }, | |
| { | |
| "path": "voices/estelle.safetensors", | |
| "sha256": "6e61e8b8dfa88d3c5ae235f8261b1ad6af0b27f5f9a8349c21458046610f8b2b", | |
| "size": 516176 | |
| } | |
| ], | |
| "languages": [ | |
| "de" | |
| ], | |
| "max_frames": 225, | |
| "mimi": { | |
| "compress": 2, | |
| "d_model": 512, | |
| "dim": 512, | |
| "ff": 2048, | |
| "heads": 8, | |
| "kernel_size": 7, | |
| "last_kernel_size": 3, | |
| "layers": 2, | |
| "ldim": 32, | |
| "n_filters": 64, | |
| "out_dim": 512, | |
| "ratios": [ | |
| 6, | |
| 5, | |
| 4 | |
| ], | |
| "residual_kernel_size": 3, | |
| "steps": 16 | |
| }, | |
| "mimi_window": 250, | |
| "prefill_len": 48, | |
| "temperature": 0.30000001192092896, | |
| "voices": [ | |
| "alba", | |
| "anna", | |
| "bill", | |
| "estelle" | |
| ] | |
| } |