Init commit

app.py

@@ -0,0 +1,42 @@
+from sclib import SoundcloudAPI, Track
+from transformers import pipeline
+import gradio as gr
+import numpy as np
+import librosa
+import os
+
+transcriber = pipeline("automatic-speech-recognition", model="ID2223/whisper-small-swedish")
+
+# do not pass a Soundcloud client ID that did not come from this library, but you can save a client_id that this lib found and reuse it
+api = SoundcloudAPI()  
+
+def get_audio(url: str):
+    filename = url_to_file(url)
+    audio_original, sr = librosa.load(filename, sr=16000)
+    audio_original = audio_original[:30*sr]
+    os.remove(filename)
+    return (sr, audio_original)
+
+def url_to_file(url: str) -> str:
+    track = api.resolve(url)
+    assert type(track) is Track
+    filename = "to_transcribe.mp3"
+    with open(filename, 'wb+') as file:
+        track.write_mp3_to(file)
+    return filename
+
+def transcribe(url: str):
+    sr, audio_original = get_audio(url)
+    audio = audio_original.astype(np.float32)
+    audio /= np.max(np.abs(audio))
+    return ((sr, audio_original), transcriber({"sampling_rate": sr, "raw": audio})["text"])
+
+
+demo = gr.Interface(
+    transcribe,
+    inputs = [gr.Textbox(label="Soundcloud URL", value="https://soundcloud.com/user-668319862/sa-gar-borsen-2024")],
+    outputs = ["audio", "text"],
+    title="Whisper Soundcloud",
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,101 @@
+aiofiles==23.2.1
+aiohttp==3.9.1
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==3.7.1
+attrs==23.1.0
+audioread==3.0.1
+beautifulsoup4==4.12.2
+bs4==0.0.1
+certifi==2023.11.17
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+decorator==5.1.1
+fastapi==0.104.1
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.46.0
+frozenlist==1.4.0
+fsspec==2023.12.1
+gradio==4.8.0
+gradio_client==0.7.1
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.25.2
+huggingface-hub==0.19.4
+idna==3.6
+importlib-resources==6.1.1
+Jinja2==3.1.2
+joblib==1.3.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kiwisolver==1.4.5
+lazy_loader==0.3
+librosa==0.10.1
+llvmlite==0.41.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+mutagen==1.47.0
+networkx==3.2.1
+numba==0.58.1
+numpy==1.26.2
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+Pillow==10.1.0
+platformdirs==4.1.0
+pooch==1.8.0
+pycparser==2.21
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.32.0
+regex==2023.10.3
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.13.2
+safetensors==0.4.1
+scikit-learn==1.3.2
+scipy==1.11.4
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+soundcloud-lib==0.6.1
+soundfile==0.12.1
+soupsieve==2.5
+soxr==0.3.7
+starlette==0.27.0
+sympy==1.12
+threadpoolctl==3.2.0
+tokenizers==0.15.0
+tomlkit==0.12.0
+toolz==0.12.0
+torch==2.1.1
+torchaudio==2.1.1
+torchvision==0.16.1
+tqdm==4.66.1
+transformers==4.35.2
+typer==0.9.0
+typing_extensions==4.9.0
+tzdata==2023.3
+urllib3==2.1.0
+uvicorn==0.24.0.post1
+websockets==11.0.3
+yarl==1.9.4