Audio transcription (Whisper) in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the Whisper model for transcription.

Prompt Engineering / GenAI

import whisper
model = whisper.load_model([1])

Drag options to blanks, or click blank then click option'

A"tiny"

B"fast"

C"large-v2"

D"small"

Attempts:

3 left

💡 Hint

Common Mistakes

Using an invalid model name like 'fast' which does not exist.

Forgetting to put the model name in quotes.

The 'tiny' model is the smallest Whisper model and is loaded with whisper.load_model("tiny").

2fill in blank

medium

Complete the code to transcribe audio using the Whisper model.

Prompt Engineering / GenAI

result = model.transcribe([1])

Drag options to blanks, or click blank then click option'

Atranscription

Baudio_data

C"audio.wav"

Dmodel

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the model object instead of the audio filename.

Passing a variable that is not the audio file path.

The transcribe method takes the path to the audio file as a string, e.g., "audio.wav".

3fill in blank

hard

Fix the error in accessing the transcribed text from the result dictionary.

Prompt Engineering / GenAI

text = result[[1]]

Drag options to blanks, or click blank then click option'

A"transcription"

B"text"

C"result"

D"output"

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'transcription' or 'output' as keys which do not exist.

Trying to access the result as an attribute instead of a dictionary key.

The transcribed text is stored under the key 'text' in the result dictionary.

4fill in blank

hard

Fill both blanks to load the model and transcribe an audio file.

Prompt Engineering / GenAI

model = whisper.load_model([1])
result = model.transcribe([2])

Drag options to blanks, or click blank then click option'

A"base"

B"audio.mp3"

C"audio.wav"

D"large"

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing model names and audio file names.

Using unsupported audio file formats.

Load the 'base' model and transcribe the audio file 'audio.wav'.

5fill in blank

hard

Fill all three blanks to extract the transcribed text and print it.

Prompt Engineering / GenAI

model = whisper.load_model([1])
result = model.transcribe([2])
print(result[[3]])

Drag options to blanks, or click blank then click option'

A"small"

B"speech.mp3"

C"text"

D"tiny"

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong keys to access the transcription.

Passing incorrect file names or model names.

Load the 'tiny' model, transcribe 'speech.mp3', and print the 'text' key from the result.