Spaces:
Runtime error
Runtime error
speech recognition
Browse files- .gitignore +7 -0
- app.py +23 -4
- requirements.txt +69 -0
.gitignore
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# .gitignore file for python projects
|
2 |
+
.venv
|
3 |
+
.env
|
4 |
+
__pycache__
|
5 |
+
*.pyc
|
6 |
+
*.pyo
|
7 |
+
*.pyd
|
app.py
CHANGED
@@ -1,7 +1,26 @@
|
|
1 |
import gradio as gr
|
|
|
|
|
2 |
|
3 |
-
|
4 |
-
return "Hello " + name + "!!"
|
5 |
|
6 |
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import gradio as gr
|
2 |
+
from transformers import pipeline
|
3 |
+
import numpy as np
|
4 |
|
5 |
+
transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
|
|
|
6 |
|
7 |
+
def transcribe(stream, new_chunk):
|
8 |
+
sr, y = new_chunk
|
9 |
+
y = y.astype(np.float32)
|
10 |
+
y /= np.max(np.abs(y))
|
11 |
+
|
12 |
+
if stream is not None:
|
13 |
+
stream = np.concatenate([stream, y])
|
14 |
+
else:
|
15 |
+
stream = y
|
16 |
+
return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
|
17 |
+
|
18 |
+
|
19 |
+
demo = gr.Interface(
|
20 |
+
transcribe,
|
21 |
+
["state", gr.Audio(sources=["microphone"], streaming=True)],
|
22 |
+
["state", "text"],
|
23 |
+
live=True,
|
24 |
+
)
|
25 |
+
|
26 |
+
demo.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
aiofiles==23.2.1
|
2 |
+
altair==5.3.0
|
3 |
+
annotated-types==0.6.0
|
4 |
+
anyio==4.3.0
|
5 |
+
attrs==23.2.0
|
6 |
+
certifi==2024.2.2
|
7 |
+
charset-normalizer==3.3.2
|
8 |
+
click==8.1.7
|
9 |
+
contourpy==1.2.1
|
10 |
+
cycler==0.12.1
|
11 |
+
exceptiongroup==1.2.0
|
12 |
+
fastapi==0.110.1
|
13 |
+
ffmpy==0.3.2
|
14 |
+
filelock==3.13.4
|
15 |
+
fonttools==4.51.0
|
16 |
+
fsspec==2024.3.1
|
17 |
+
gradio==4.26.0
|
18 |
+
gradio_client==0.15.1
|
19 |
+
h11==0.14.0
|
20 |
+
httpcore==1.0.5
|
21 |
+
httpx==0.27.0
|
22 |
+
huggingface-hub==0.22.2
|
23 |
+
idna==3.7
|
24 |
+
importlib_resources==6.4.0
|
25 |
+
Jinja2==3.1.3
|
26 |
+
jsonschema==4.21.1
|
27 |
+
jsonschema-specifications==2023.12.1
|
28 |
+
kiwisolver==1.4.5
|
29 |
+
markdown-it-py==3.0.0
|
30 |
+
MarkupSafe==2.1.5
|
31 |
+
matplotlib==3.8.4
|
32 |
+
mdurl==0.1.2
|
33 |
+
numpy==1.26.4
|
34 |
+
orjson==3.10.0
|
35 |
+
packaging==24.0
|
36 |
+
pandas==2.2.2
|
37 |
+
pillow==10.3.0
|
38 |
+
pydantic==2.7.0
|
39 |
+
pydantic_core==2.18.1
|
40 |
+
pydub==0.25.1
|
41 |
+
Pygments==2.17.2
|
42 |
+
pyparsing==3.1.2
|
43 |
+
python-dateutil==2.9.0.post0
|
44 |
+
python-multipart==0.0.9
|
45 |
+
pytz==2024.1
|
46 |
+
PyYAML==6.0.1
|
47 |
+
referencing==0.34.0
|
48 |
+
regex==2023.12.25
|
49 |
+
requests==2.31.0
|
50 |
+
rich==13.7.1
|
51 |
+
rpds-py==0.18.0
|
52 |
+
ruff==0.3.7
|
53 |
+
safetensors==0.4.2
|
54 |
+
semantic-version==2.10.0
|
55 |
+
shellingham==1.5.4
|
56 |
+
six==1.16.0
|
57 |
+
sniffio==1.3.1
|
58 |
+
starlette==0.37.2
|
59 |
+
tokenizers==0.15.2
|
60 |
+
tomlkit==0.12.0
|
61 |
+
toolz==0.12.1
|
62 |
+
tqdm==4.66.2
|
63 |
+
transformers==4.39.3
|
64 |
+
typer==0.12.3
|
65 |
+
typing_extensions==4.11.0
|
66 |
+
tzdata==2024.1
|
67 |
+
urllib3==2.2.1
|
68 |
+
uvicorn==0.29.0
|
69 |
+
websockets==11.0.3
|