Create audio_to_text.py

audio_to_text.py

@@ -0,0 +1,23 @@
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+import torchaudio
+
+
+# load model and processor
+processor = WhisperProcessor.from_pretrained("openai/whisper-tiny")
+model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny")
+model.config.forced_decoder_ids = None
+
+
+def audio_to_text(file_path_abs):
+    # Load the audio and resample it
+    waveform, sample_rate = torchaudio.load(file_path_abs)
+    resampler = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)
+    waveform = resampler(waveform)
+    waveform = waveform.squeeze().numpy()
+    input_features = processor(waveform, sampling_rate=16000, return_tensors="pt").input_features
+
+    # generate token ids
+    predicted_ids = model.generate(input_features)
+    # decode token ids to text
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+    return transcription