vasista22 commited on
Commit
fb42807
1 Parent(s): 2f9937c

inference_code_snippet_added

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -55,6 +55,21 @@ In order to infer a single audio file using this model, the following code snipp
55
  >>> print('Transcription: ', transcribe(audio)["text"])
56
  ```
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ## Training and evaluation data
59
 
60
  Training Data:
 
55
  >>> print('Transcription: ', transcribe(audio)["text"])
56
  ```
57
 
58
+ For faster inference of whisper models the [whisper-jax](https://github.com/sanchit-gandhi/whisper-jax) library can be used. Please follow the necessary installation steps as mentioned [here](https://github.com/vasistalodagala/whisper-finetune#faster-evaluation-with-whisper-jax), before using the following code snippet:
59
+
60
+ ```python
61
+ >>> import jax.numpy as jnp
62
+ >>> from whisper_jax import FlaxWhisperForConditionalGeneration, FlaxWhisperPipline
63
+
64
+ >>> # path to the audio file to be transcribed
65
+ >>> audio = "/path/to/audio.format"
66
+
67
+ >>> transcribe = FlaxWhisperPipline("vasista22/whisper-kannada-medium", batch_size=16)
68
+ >>> transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="kn", task="transcribe")
69
+
70
+ >>> print('Transcription: ', transcribe(audio)["text"])
71
+ ```
72
+
73
  ## Training and evaluation data
74
 
75
  Training Data: