I have tried to deploy a web-app (just a proof of concept) to take an audio file and transcribe it. It works fine on my localhost but in the cloud it runs into a run-time error when transcribing. I also built the requirements.txt from scratch with pipreq but it doesn’t change anything. This is the error:
Error: Traceback (most recent call last): File “/home/adminuser/venv/bin/whisper”, line 5, in from whisper.transcribe import cli File “/home/adminuser/venv/lib/python3.10/site-packages/whisper/init .py”, line 13, in from .model import ModelDimensions, Whisper File “/home/adminuser/venv/lib/python3.10/site-packages/whisper/model.py”, line 13, in from .transcribe import transcribe as transcribe_function File “/home/adminuser/venv/lib/python3.10/site-packages/whisper/transcribe.py”, line 20, in from .timing import add_word_timestamps File “/home/adminuser/venv/lib/python3.10/site-packages/whisper/timing.py”, line 7, in import numba File “/home/adminuser/venv/lib/python3.10/site-packages/numba/init .py”, line 55, in _ensure_critical_deps() File “/home/adminuser/venv/lib/python3.10/site-packages/numba/init .py”, line 42, in _ensure_critical_deps raise ImportError(“Numba needs NumPy 1.24 or less”) ImportError: Numba needs NumPy 1.24 or less
I have tried to explicitly include the above numPy and Numba versions but no chance.
Does anybody have a hint?
Thanks
By the way: the error does not show in the manage-app sidebar but directly in the st.write field where the transcript is supposed to be:
Hi @Awindbrake,
Thanks for posting! Can you share your requirements.txt?
You might resolve the error by specifying the correct versions:
numpy==1.24.0
numba==0.54.0
Let me know if this resolves the issue for you.
Thanks so much. I tried it but it didn’t help. This is what my requirements.txt says:
beautifulsoup4==4.11.2
docx==0.2.4
langchain==0.0.271
nltk==3.8.1
openai==0.27.6
pandas==2.0.2
pdfplumber==0.9.0
python_docx==0.8.11
rake_nltk==1.0.6
Requests==2.31.0
spacy==3.5.2
streamlit==1.25.0
numpy==1.24.0
numba==0.54.0
Can you share your code as well so I can troubleshoot it for you?
Sure. It is not much until now… just starting with the basics:
Many thanks in advance
#Define case 5
def whisper():
with st.form('audio form'):
API = API2
uploaded_file = st.file_uploader("Upload your audio file here...")
# submit button
submitted = st.form_submit_button("Transcribe audio")
if submitted:
# Save the uploaded file to disk
audio_file_path = os.path.join(os.getcwd(), "temp_audio_file")
with open(audio_file_path, 'wb') as f:
f.write(uploaded_file.getvalue())
# Start the process
process = subprocess.Popen(["whisper", audio_file_path], stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
# Get both stdout and stderr outputs at once
stdout_data, stderr_data = process.communicate()
# Process stdout_data to remove timestamps and display on Streamlit
for line in stdout_data.splitlines():
clean_line = re.sub(r'\[\d{2}:\d{2}\.\d{3} --> \d{2}:\d{2}\.\d{3}\] ', '', line)
st.write("success")
# Check for errors
if process.returncode != 0:
st.write(f"Error: {stderr_data}")
# Optionally, delete the temporary file
os.remove(audio_file_path)
this is solved in the meantime. This works:
def whisper():
transcript=“”
# Define a function to preprocess and truncate the text
def preprocess_and_truncate(text, max_length=7000):
processed_text = text[:max_length] # Truncate to the specified max_length
return processed_text
if 'transcript' not in st.session_state:
st.session_state.transcript = ""
if 'summary' not in st.session_state:
st.session_state.summary = ""
with st.form('audio form'):
openai.api_key = API2
uploaded_file = st.file_uploader("Upload your audio file here (wav, mp3, mp4, m4a, mpeg, mpga): ")
#system_message = "Act as business consultant specialized in Know-your-customer analysis and topics around German export control."
# submit button
submitted = st.form_submit_button("Transcribe audio")
if submitted:
if uploaded_file:
# Start the transcription process using the uploaded file
transcription = openai.Audio.transcribe("whisper-1", uploaded_file)
transcript = transcription['text']
# Preprocess and truncate the transcript
processed_transcript = preprocess_and_truncate(transcript, max_length=7000) # Adjust the max_length as needed
formatted_transcript = transcript.replace("\n", "<br>").replace(".", ".<br>").replace("?", "?<br>").replace("!", "!<br>")
st.markdown("### Transcript:")
st.write(formatted_transcript, unsafe_allow_html=True)
#st.text_area("Transcript:", transcript, height=200)
prompt =f"summarize this in English language in a concise way in up to 10 full sentences using bullet points. Here is the context: {processed_transcript}"
summary = generate_text(prompt,"you are a helpful assistant",GPT_model, 0.5, 700)
st.markdown("### Summary:")
st.write(summary)
# Combine the transcript and summary for download
combined_text = f"Transcript:\n{processed_transcript}\n\nSummary:\n{summary}"
# Add a single download button for both transcript and summary
st.download_button('Download Transcript and Summary', combined_text, file_name='transcript_summary.txt')
