Update README.md

README.md

@@ -64,9 +64,30 @@ The following hyperparameters were used during training:
 
 ### Inference
 
+#### HF
+
+```python
+from transformers import pipeline
+pipe = pipeline("automatic-speech-recognition", model="imvladikon/whisper-medium-he", device_map="auto") # requires `pip install accelerate`
+print(recognize("sample.mp3"))
+```
+
 #### whisper.cpp
 
-check : https://huggingface.co/imvladikon/whisper-medium-he/blob/main/ggml-hebrew.bin
+Prepared : https://huggingface.co/imvladikon/whisper-medium-he/blob/main/ggml-hebrew.bin
+
+But if need to convert:
+```bash
+git clone https://github.com/openai/whisper
+git clone https://github.com/ggerganov/whisper.cpp
+git clone https://huggingface.co/imvladikon/whisper-medium-he
+python3 ./whisper.cpp/models/convert-h5-to-ggml.py ./whisper-medium-he/ ./whisper .
+```
+
+Then possible to check (if produced model is `ggml-model.bin`):
+```bash
+cd whisper.cpp && ./main -m ../ggml-model.bin -f ../sample.wav
+```
 
 ### Framework versions