Upload 10 files

README.md

@@ -0,0 +1,13 @@
+---
+title: Audioclassification
+emoji: 💻
+colorFrom: gray
+colorTo: indigo
+sdk: gradio
+sdk_version: 2.9.4
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,88 @@
+import gradio
+import torchaudio
+from fastai.vision.all import *
+from fastai.learner import load_learner
+from torchvision.utils import save_image
+from huggingface_hub import hf_hub_download
+
+
+model = load_learner(
+    hf_hub_download("kurianbenoy/music_genre_classification_baseline", "model.pkl")
+)
+
+
+EXAMPLES_PATH = Path("./examples")
+labels = model.dls.vocab
+
+interface_options = {
+    "title": "Music Genre Classification",
+    "description": " ",
+    "interpretation": "default",
+    "layout": "horizontal",
+    # Audio from validation file
+    "examples": ["000003.ogg", "000032.ogg", "000038.ogg", "000050.ogg", "000103.ogg"],
+    "allow_flagging": "never"
+}
+
+## Code from Dien Hoa Truong inference notebook: https://www.kaggle.com/code/dienhoa/inference-submission-music-genre
+N_FFT = 2048
+HOP_LEN = 1024
+
+
+def create_spectrogram(filename):
+    audio, sr = torchaudio.load(filename)
+    specgram = torchaudio.transforms.MelSpectrogram(
+        sample_rate=sr,
+        n_fft=N_FFT,
+        win_length=N_FFT,
+        hop_length=HOP_LEN,
+        center=True,
+        pad_mode="reflect",
+        power=2.0,
+        norm="slaney",
+        onesided=True,
+        n_mels=224,
+        mel_scale="htk",
+    )(audio).mean(axis=0)
+    specgram = torchaudio.transforms.AmplitudeToDB()(specgram)
+    specgram = specgram - specgram.min()
+    specgram = specgram / specgram.max()
+
+    return specgram
+
+
+def create_image(filename):
+    specgram = create_spectrogram(filename)
+    dest = Path("temp.png")
+    save_image(specgram, "temp.png")
+
+
+# Code from: https://huggingface.co/spaces/suvash/food-101-resnet50
+def predict(img):
+    img = PILImage.create(img)
+    _pred, _pred_w_idx, probs = model.predict(img)
+    # gradio doesn't support tensors, so converting to float
+    labels_probs = {labels[i]: float(probs[i]) for i, _ in enumerate(labels)}
+    return labels_probs
+
+
+def end2endpipeline(filename):
+    create_image(filename)
+    return predict("temp.png")
+
+
+demo = gradio.Interface(
+    fn=end2endpipeline,
+    inputs=gradio.inputs.Audio(source="upload", type="filepath"),
+    outputs=gradio.outputs.Label(num_top_classes=5),
+    **interface_options,
+)
+
+launch_options = {
+    "enable_queue": True,
+    "share": False,
+    # thanks Alex for pointing this option to cache examples
+    "cache_examples": True,
+}
+
+demo.launch(**launch_options)

article.md

@@ -0,0 +1,44 @@
+> Note: The examples provides doesn't work on Safari, in case people are trying to access on a Mac. Please try it in a different browser.
+
+During first lesson of Practical Deep Learning for Coders course, Jeremy had mentioned how using simple computer vision model by being a bit creative we can build a state of the art model to classify audio with same image classification model. I was curious on how I can train an music classifier, as I have never worked on audio data problems before.
+
+
+[You can find how I trained this music genre classification using fast.ai in this blogpost.](https://kurianbenoy.com/posts/2022/2022-05-01-audiocnndemo.html).
+
+## Dataset
+
+1. [The competition data](https://www.kaggle.com/competitions/kaggle-pog-series-s01e02/data)
+2. [Image data generated from converting audio to melspectograms in form of images](https://www.kaggle.com/datasets/dienhoa/music-genre-spectrogram-pogchamps)
+
+
+## Training
+
+Fast.ai was used to train this classifier with a ResNet50 vision learner for 10 epochs.
+
+| epoch	| train_loss	| valid_loss	| error_rate	| time  |
+|-------|---------------|---------------|---------------|-------|
+|0  |	2.312176 |	1.843815 |	0.558654 |	02:07 |
+|1  |	2.102361 |	1.719162 |	0.539061 |	02:08 |
+|2  |	1.867139 |	1.623988 |	0.527003 |	02:08 |
+|3  |	1.710557 |	1.527913 |	0.507661 |	02:07 |
+|4  |	1.629478 |	1.456836 |	0.479779 |	02:05 |
+|5  |	1.519305 |	1.433036 |	0.474253 |	02:05 |
+|6  |	1.457465 |	1.379757 |	0.464456 |	02:05 |
+|7  |	1.396283 |	1.369344 |	0.457925 |	02:05 |
+|8  |	1.359388 |	1.367973 |	0.453655 |	02:05 |
+|9  |	1.364363 |	1.368887 |	0.456167 |	02:04 |
+
+
+## Examples
+
+The example images provided in the demo are from the validation data from Kaggle competition data, which was not used during training.
+
+## Credits
+
+Thanks [Dien Hoa Truong](https://twitter.com/DienhoaT) for providing [inference code](https://www.kaggle.com/code/dienhoa/inference-submission-music-genre) for creating end to end pipeline from creating audio to converting to melspectograms, and then doing prediction.
+
+Thanks [@suvash](https://twitter.com/suvash) for helping me get started with huggingface
+spaces and for his [excellent space](https://huggingface.co/spaces/suvash/food-101-resnet50) which was a reference for this work.
+
+Thanks [@strickvl](https://twitter.com/strickvl) for reporting issue in safari browser
+and trying this space out.

gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,5 @@
+fastai==2.6.0
+gradio==2.9.4
+torchaudio
+torchvision
+huggingface_hub