Spaces:
Sleeping
Sleeping
Commit
·
3ecb0fd
1
Parent(s):
ad79b29
Update app.py
Browse files
app.py
CHANGED
@@ -1,17 +1,21 @@
|
|
1 |
import gradio as gr
|
2 |
from transformers import pipeline
|
3 |
-
import
|
4 |
|
|
|
5 |
asr_model = pipeline("automatic-speech-recognition", model="openai/whisper-small")
|
6 |
|
7 |
def transcribe(audio_file):
|
8 |
-
|
|
|
|
|
9 |
transcription = asr_model(data, sampling_rate=samplerate)
|
10 |
return transcription["text"]
|
11 |
|
|
|
12 |
iface = gr.Interface(
|
13 |
fn=transcribe,
|
14 |
-
inputs="
|
15 |
outputs="text"
|
16 |
)
|
17 |
|
|
|
1 |
import gradio as gr
|
2 |
from transformers import pipeline
|
3 |
+
import librosa
|
4 |
|
5 |
+
# Initialize the model
|
6 |
asr_model = pipeline("automatic-speech-recognition", model="openai/whisper-small")
|
7 |
|
8 |
def transcribe(audio_file):
|
9 |
+
# Load the audio file with librosa
|
10 |
+
data, samplerate = librosa.load(audio_file.name, sr=None)
|
11 |
+
# Pass the audio data to the model for transcription
|
12 |
transcription = asr_model(data, sampling_rate=samplerate)
|
13 |
return transcription["text"]
|
14 |
|
15 |
+
# Create the Gradio interface
|
16 |
iface = gr.Interface(
|
17 |
fn=transcribe,
|
18 |
+
inputs=gr.inputs.Audio(source="microphone", type="file"),
|
19 |
outputs="text"
|
20 |
)
|
21 |
|