Instructions to use MacEpic/pocket-tts-it-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use MacEpic/pocket-tts-it-coreml with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("MacEpic/pocket-tts-it-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-it-coreml: direct link, hf CLI and curl.
- Browser
- Download file 3.45 kB
-
https://huggingface.co/MacEpic/pocket-tts-it-coreml/resolve/main/bundle.json
- Command line
-
hf download hf://MacEpic/pocket-tts-it-coreml/bundle.json
-
curl -L -o bundle.json https://huggingface.co/MacEpic/pocket-tts-it-coreml/resolve/main/bundle.json
3.45 kB
| { | |
| "built": 1794179339, | |
| "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": "0aac583fbb981a067df2aff6667737e4c6169ec9be3006eb1fd4e76b6e31cb7a", | |
| "size": 323041 | |
| }, | |
| { | |
| "path": "flow-c415-t1.mlpackage/Data/com.apple.CoreML/weights/weight.bin", | |
| "sha256": "43580247e216cf7f021b63dac181441da05444721cbef4f78912213225355612", | |
| "size": 168889280 | |
| }, | |
| { | |
| "path": "flow-c415-t1.mlpackage/Manifest.json", | |
| "sha256": "b1fba73e8b331e8b63c39afb4fd2cd3cb013bee50e537ef0cd87995bfbe2e3ed", | |
| "size": 534 | |
| }, | |
| { | |
| "path": "flow-c415-t48.mlpackage/Data/com.apple.CoreML/model.mlmodel", | |
| "sha256": "93a1a0e3eb1bf923433f7500fb080460bf3b5aad318d8947b7ccff930f41861c", | |
| "size": 323041 | |
| }, | |
| { | |
| "path": "flow-c415-t48.mlpackage/Data/com.apple.CoreML/weights/weight.bin", | |
| "sha256": "43580247e216cf7f021b63dac181441da05444721cbef4f78912213225355612", | |
| "size": 168889280 | |
| }, | |
| { | |
| "path": "flow-c415-t48.mlpackage/Manifest.json", | |
| "sha256": "33a516e7481df4e3926194c800d76c25ab077818028741d31e04e74a3e46b097", | |
| "size": 534 | |
| }, | |
| { | |
| "path": "host.safetensors", | |
| "sha256": "3450ec4e31b87818c8ee9d016ee8383715df361ee49f05fb25f9aa50e67fc80c", | |
| "size": 16523760 | |
| }, | |
| { | |
| "path": "mimi-c266.mlpackage/Data/com.apple.CoreML/model.mlmodel", | |
| "sha256": "304de35c3b8b3a149c049ab5846ce154ab05f4382010e4481b3f06ed2da5e88d", | |
| "size": 131135 | |
| }, | |
| { | |
| "path": "mimi-c266.mlpackage/Data/com.apple.CoreML/weights/weight.bin", | |
| "sha256": "2e7d230184aa1bc8b1426cdecf814a408726887fa84aa05e3b54defc87db9c35", | |
| "size": 41182464 | |
| }, | |
| { | |
| "path": "mimi-c266.mlpackage/Manifest.json", | |
| "sha256": "94b38f6914ff087b76c8189f1d8b7599e576d91a103d6f9ee6e2d83c305d964f", | |
| "size": 534 | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "sha256": "4bc1c0d4d54f9480183e94c94cfabf74fd89b0912537d4ef607d1982c4a381ec", | |
| "size": 246586 | |
| }, | |
| { | |
| "path": "voices/alba.safetensors", | |
| "sha256": "5f5c97d646c1dc4fee0b6348d95a3fed741da02ca6a2795fc397229c67d87974", | |
| "size": 516176 | |
| }, | |
| { | |
| "path": "voices/anna.safetensors", | |
| "sha256": "19a4dce4534e64f3e1bdacfe8e550a9d331e046553dba782d87a064f0eb15325", | |
| "size": 516176 | |
| }, | |
| { | |
| "path": "voices/bill.safetensors", | |
| "sha256": "ac5a5bdf50f6be20907ebab756d8ecd35f101c69579b79c3938f1b5f86c5286b", | |
| "size": 516176 | |
| }, | |
| { | |
| "path": "voices/estelle.safetensors", | |
| "sha256": "f89d576831bd00ee7964bbe791f9169ef1acd813afc6464aef3de0c6d47908dc", | |
| "size": 516176 | |
| } | |
| ], | |
| "languages": [ | |
| "it" | |
| ], | |
| "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" | |
| ] | |
| } |