Google has a page describing how to use one of their Gemini-1.5 models to transcribe audio. They include a sample script (see below). The script grabs the audio file from Google Storage via the Part.from_uri() command. I would, instead, like to use a local file. Setting the URI to "file:///..." does not work. How can I do that? Google's (working, cloud-based) code is here: import vertexai from vertexai.generative_models import GenerativeModel, GenerationConfig, Part # TODO(developer): Update and un-comment below line # PROJECT_ID = "your-project-id" vertexai.init(project=PROJECT_ID, location="us-central1") model = GenerativeModel("gemini-1.5-flash-002") prompt = """ Can you transcribe this interview, in the format of timecode, speaker, caption. Use speaker A, speaker B, etc. to identify speakers. """ audio_file_uri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3" audio_file = Part.from_uri(audio_file_uri, mime_type="audio/mpeg") contents = [audio_file, prompt] response = model.generate_content(contents, generation_config=GenerationConfig(audio_timestamp=True)) print(response.text) # Example response: # [00:00:00] Speaker A: Your devices are getting better over time... # [00:00:16] Speaker B: Welcome to the Made by Google podcast, ... # [00:01:00] Speaker A: So many features. I am a singer. ... # [00:01:33] Speaker B: Amazing. DeCarlos, same question to you, ... Continue reading...
