Instructions to use hon9kon9ize/speech2phone-ctc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hon9kon9ize/speech2phone-ctc with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hon9kon9ize/speech2phone-ctc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download speech_tokenizer_v2.onnx from hon9kon9ize/speech2phone-ctc: direct link, hf CLI and curl.
- Browser
- Download file 496 MB
-
https://huggingface.co/hon9kon9ize/speech2phone-ctc/resolve/main/speech_tokenizer_v2.onnx
- Command line
-
hf download hf://hon9kon9ize/speech2phone-ctc/speech_tokenizer_v2.onnx
-
curl -L -o speech_tokenizer_v2.onnx https://huggingface.co/hon9kon9ize/speech2phone-ctc/resolve/main/speech_tokenizer_v2.onnx
496 MB
- Xet hash:
- 03dd09d325504ceb27ed0cfc89a76fb9a3527949179187aca2a983a6dd8f34d8
- Size of remote file:
- 496 MB
- SHA256:
- d43342aa12163a80bf07bffb94c9de2e120a8df2f9917cd2f642e7f4219c6f71
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.