fix: ffmpeg_microphone_live key error

kotoba_whisper.py

@@ -155,14 +155,14 @@ class KotobaWhisperPipeline(AutomaticSpeechRecognitionPipeline):
             inputs = ffmpeg_read(inputs, self.feature_extractor.sampling_rate)
         if isinstance(inputs, dict):
             # Accepting `"array"` which is the key defined in `datasets` for better integration
-            if not ("sampling_rate" in inputs and "array" in inputs):
+            if not ("sampling_rate" in inputs and ("raw" in inputs or "array" in inputs)):
                 raise ValueError(
                     "When passing a dictionary to AutomaticSpeechRecognitionPipeline, the dict needs to contain a "
                     '"array" key containing the numpy array representing the audio and a "sampling_rate" key, '
                     "containing the sampling_rate associated with that array"
                 )
             in_sampling_rate = inputs.pop("sampling_rate")
-            inputs = inputs.pop("array", None)
+            inputs = inputs.pop("array", inputs.pop("raw", None))
             if in_sampling_rate != self.feature_extractor.sampling_rate:
                 if is_torchaudio_available():
                     from torchaudio import functional as F