Automatic Speech Recognition
K2
ONNX
Hebrew
speech
asr
hebrew
streaming
zipformer
transducer
icefall
sherpa-onnx
proof-of-concept
Instructions to use Hebrish/Gefilte with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- K2
How to use Hebrish/Gefilte with K2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download train_log.jsonl from Hebrish/Gefilte: direct link, hf CLI and curl.
- Browser
- Download file 949 Bytes
-
https://huggingface.co/Hebrish/Gefilte/resolve/main/train_log.jsonl
- Command line
-
hf download hf://Hebrish/Gefilte/train_log.jsonl
-
curl -L -o train_log.jsonl https://huggingface.co/Hebrish/Gefilte/resolve/main/train_log.jsonl
949 Bytes
| {"epoch": 1, "step": 11, "loss_per_frame": 0.1474, "lr": 0.001999999995} | |
| {"epoch": 2, "step": 22, "loss_per_frame": 0.1028, "lr": 0.0019999499810753173} | |
| {"epoch": 3, "step": 33, "loss_per_frame": 0.09, "lr": 0.001999799998790127} | |
| {"epoch": 4, "step": 44, "loss_per_frame": 0.0756, "lr": 0.001999550160525066} | |
| {"epoch": 5, "step": 55, "loss_per_frame": 0.066, "lr": 0.0019992006532995347} | |
| {"epoch": 6, "step": 66, "loss_per_frame": 0.0586, "lr": 0.0019987517383521945} | |
| {"epoch": 7, "step": 77, "loss_per_frame": 0.0547, "lr": 0.001998203750556328} | |
| {"epoch": 8, "step": 88, "loss_per_frame": 0.0508, "lr": 0.001997557097672705} | |
| {"epoch": 9, "step": 99, "loss_per_frame": 0.0469, "lr": 0.001996812259443309} | |
| {"epoch": 10, "step": 110, "loss_per_frame": 0.0426, "lr": 0.001995969786529987} | |
| {"epoch": 11, "step": 121, "loss_per_frame": 0.0398, "lr": 0.001995030299302731} | |
| {"epoch": 12, "step": 132, "loss_per_frame": 0.0373, "lr": 0.0019939944864829423} | |