Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
# Transform an audio to text script with language detection.
|
2 |
# Author: Pratiksha Patel
|
3 |
-
|
4 |
# Description: This script record the audio, transform it to text, detect the language of the file and save it to a txt file.
|
5 |
# import required modules
|
6 |
import os
|
@@ -9,17 +8,12 @@ import streamlit as st
|
|
9 |
from audio_recorder_streamlit import audio_recorder
|
10 |
from langdetect import detect
|
11 |
import numpy as np
|
12 |
-
# Use a pipeline as a high-level helper
|
13 |
-
#from transformers import pipeline
|
14 |
-
#pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large")
|
15 |
-
# Load model directly
|
16 |
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
|
17 |
|
18 |
def transcribe_audio(audio_bytes):
|
19 |
processor = AutoProcessor.from_pretrained("openai/whisper-large")
|
20 |
model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large")
|
21 |
audio_array = np.frombuffer(audio_bytes, dtype=np.int16)
|
22 |
-
# Cast audio array to double precision and normalize
|
23 |
audio_tensor = torch.tensor(audio_array, dtype=torch.float64) / 32768.0
|
24 |
input_values = processor(audio_tensor, return_tensors="pt", sampling_rate=16000).input_values
|
25 |
logits = model(input_values).logits
|
@@ -27,17 +21,6 @@ def transcribe_audio(audio_bytes):
|
|
27 |
transcription = processor.decode(predicted_ids[0])
|
28 |
return transcription
|
29 |
|
30 |
-
# Function to open a file
|
31 |
-
#def startfile(fn):
|
32 |
-
# os.system('open %s' % fn)
|
33 |
-
|
34 |
-
# Function to create and open a txt file
|
35 |
-
#def create_and_open_txt(text, filename):
|
36 |
-
# Create and write the text to a txt file
|
37 |
-
# with open(filename, "w") as file:
|
38 |
-
# file.write(text)
|
39 |
-
# startfile(filename)
|
40 |
-
|
41 |
# Streamlit app
|
42 |
st.title("Audio to Text Transcription..")
|
43 |
|
@@ -55,9 +38,3 @@ if audio_bytes:
|
|
55 |
st.write("Error: Failed to transcribe audio.")
|
56 |
else:
|
57 |
st.write("No audio recorded.")
|
58 |
-
# Detect the language
|
59 |
-
#language = detect(transcription)
|
60 |
-
#st.write(f"Detected language: {language}")
|
61 |
-
|
62 |
-
# Create and open a txt file with the text
|
63 |
-
#create_and_open_txt(transcription, f"output_{language}.txt")
|
|
|
1 |
# Transform an audio to text script with language detection.
|
2 |
# Author: Pratiksha Patel
|
|
|
3 |
# Description: This script record the audio, transform it to text, detect the language of the file and save it to a txt file.
|
4 |
# import required modules
|
5 |
import os
|
|
|
8 |
from audio_recorder_streamlit import audio_recorder
|
9 |
from langdetect import detect
|
10 |
import numpy as np
|
|
|
|
|
|
|
|
|
11 |
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
|
12 |
|
13 |
def transcribe_audio(audio_bytes):
|
14 |
processor = AutoProcessor.from_pretrained("openai/whisper-large")
|
15 |
model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large")
|
16 |
audio_array = np.frombuffer(audio_bytes, dtype=np.int16)
|
|
|
17 |
audio_tensor = torch.tensor(audio_array, dtype=torch.float64) / 32768.0
|
18 |
input_values = processor(audio_tensor, return_tensors="pt", sampling_rate=16000).input_values
|
19 |
logits = model(input_values).logits
|
|
|
21 |
transcription = processor.decode(predicted_ids[0])
|
22 |
return transcription
|
23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
# Streamlit app
|
25 |
st.title("Audio to Text Transcription..")
|
26 |
|
|
|
38 |
st.write("Error: Failed to transcribe audio.")
|
39 |
else:
|
40 |
st.write("No audio recorded.")
|
|
|
|
|
|
|
|
|
|
|
|