Update README.md

README.md

@@ -189,7 +189,7 @@ To each task corresponds a sequence of tokens that are given to the decoder as *
 
 # Usage
 
-To transcribe or translate audio files, the model has to be used along a `WhisperFeatureExtractor`.
+To transcribe or translate audio files, the model has to be used along a `WhisperProcessor`. The `WhisperProcessor.get_decoder_prompt_ids` function is used to get a list of `( idx, token )` tuples, which can either be set in the config, or directly passed to the generate function, as `forced_decoder_ids`. 
 
 
 ## Transcription 
@@ -238,7 +238,7 @@ transcription.
 >>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
 >>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=16_000))
 >>> input_speech = next(iter(ds))["audio"]["array"]
->>> # tokenize
+>>> model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language = "fr", task = "transcribe")
 >>> input_features = processor(input_speech, return_tensors="pt").input_features 
 >>> predicted_ids = model.generate(input_features)
 >>> transcription = processor.batch_decode(predicted_ids)
@@ -268,7 +268,7 @@ The "<|translate|>" is used as the first decoder input token to specify the tran
 >>> input_speech = next(iter(ds))["audio"]["array"]
 >>> # tokenize
 >>> input_features = processor(input_speech, return_tensors="pt").input_features 
->>> forced_decoder_ids = processor._get_decoder_prompt_ids(language = "fr", task = "translate")
+>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language = "fr", task = "translate")
 
 >>> predicted_ids = model.generate(input_features, forced_decoder_ids = forced_decoder_ids)
 >>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)