Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,10 +1,8 @@
|
|
1 |
import gradio as gr
|
2 |
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
|
3 |
import torch
|
4 |
-
import requests
|
5 |
-
import os
|
6 |
|
7 |
-
model_id = "distil-whisper/distil-large-
|
8 |
|
9 |
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
10 |
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
|
@@ -17,26 +15,27 @@ model.to(device)
|
|
17 |
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
|
18 |
processor = AutoProcessor.from_pretrained(model_id)
|
19 |
|
20 |
-
|
21 |
-
"automatic-speech-recognition",
|
22 |
-
model=model,
|
23 |
-
tokenizer=processor.tokenizer,
|
24 |
-
feature_extractor=processor.feature_extractor,
|
25 |
-
max_new_tokens=128,
|
26 |
-
torch_dtype=torch_dtype,
|
27 |
-
device=device,
|
28 |
-
)
|
29 |
|
30 |
def transcribe_audio(audio_file):
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
outputs = gr.Textbox()
|
40 |
|
41 |
-
interface = gr.Interface(
|
|
|
|
|
42 |
interface.launch()
|
|
|
1 |
import gradio as gr
|
2 |
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
|
3 |
import torch
|
|
|
|
|
4 |
|
5 |
+
model_id = "distil-whisper/distil-large-v3"
|
6 |
|
7 |
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
8 |
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
|
|
|
15 |
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
|
16 |
processor = AutoProcessor.from_pretrained(model_id)
|
17 |
|
18 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
def transcribe_audio(audio_file):
|
21 |
+
pipe = pipeline(
|
22 |
+
"automatic-speech-recognition",
|
23 |
+
model=model,
|
24 |
+
tokenizer=processor.tokenizer,
|
25 |
+
feature_extractor=processor.feature_extractor,
|
26 |
+
max_new_tokens=128,
|
27 |
+
torch_dtype=torch_dtype,
|
28 |
+
device=device,
|
29 |
+
)
|
30 |
+
results = pipe(audio_file)
|
31 |
+
return results["text"]
|
32 |
+
|
33 |
+
inputs = [
|
34 |
+
gr.Audio(sources="upload", type="filepath"),
|
35 |
+
]
|
36 |
outputs = gr.Textbox()
|
37 |
|
38 |
+
interface = gr.Interface(
|
39 |
+
fn=transcribe_audio, inputs=inputs, outputs=outputs, title="Audio Transcription App"
|
40 |
+
)
|
41 |
interface.launch()
|