jonatasgrosman commited on
Commit
5881c3b
1 Parent(s): ee165c0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -44,15 +44,15 @@ The script used for training can be found here: https://github.com/jonatasgrosma
44
 
45
  The model can be used directly (without a language model) as follows...
46
 
47
- Using the [ASRecognition](https://github.com/jonatasgrosman/asrecognition) library:
48
 
49
  ```python
50
- from asrecognition import ASREngine
51
 
52
- asr = ASREngine("ar", model_path="jonatasgrosman/wav2vec2-large-xlsr-53-arabic")
 
53
 
54
- audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
55
- transcriptions = asr.transcribe(audio_paths)
56
  ```
57
 
58
  Writing your own inference script:
 
44
 
45
  The model can be used directly (without a language model) as follows...
46
 
47
+ Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
48
 
49
  ```python
50
+ from huggingsound import SpeechRecognitionModel
51
 
52
+ model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-arabic")
53
+ audio_paths = ["/path/to/sagan.mp3", "/path/to/asimov.wav"]
54
 
55
+ transcriptions = model.transcribe(audio_paths)
 
56
  ```
57
 
58
  Writing your own inference script: