Commit

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.keras filter=lfs diff=lfs merge=lfs -text
+functions/*.keras filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+*.ipynb
+*/*.ipynb
+.DS_Store
+*/.DS_Store
+test/

README.md

@@ -0,0 +1,12 @@
+---
+title: Sponsoredbye
+emoji: 🦀
+colorFrom: pink
+colorTo: purple
+sdk: gradio
+sdk_version: 4.31.4
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

RNN_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642ec9499996ca6dcd3c8f2874ae3c5d9ca0095064d2f8faae1f12b2fea1e020
+size 3974964

app.py

@@ -0,0 +1,35 @@
+from os import pipe
+import re
+import gradio as gr
+from functions.punctuation import punctuate
+from functions.model_infer import predict_from_document
+
+
+title = "sponsoredBye - never listen to sponsors again"
+description = "Sponsored sections in videos are annoying and take up a lot of time. Improve your YouTube watching experience, by filling in the youtube url and figure out what segments to skip."
+article = "Check out [the original Rick and Morty Bot](https://huggingface.co/spaces/kingabzpro/Rick_and_Morty_Bot) that this demo is based off of."
+
+
+def pipeline(video_url):
+    video_id = video_url.split("?v=")[-1]
+    punctuated_text = punctuate(video_id)
+    sentences = re.split(r"[\.\!\?]\s", punctuated_text)
+    classification = predict_from_document(sentences)
+    #    return punctuated_text
+    return [{"start": "12:05", "end": "12:52", "classification": str(classification)}]
+
+
+# print(pipeline("VL5M5ZihJK4"))
+demo = gr.Interface(
+    fn=pipeline,
+    title=title,
+    description=description,
+    inputs="text",
+    #    outputs=gr.Label(num_top_classes=3),
+    outputs="json",
+    examples=[
+        "https://www.youtube.com/watch?v=VL5M5ZihJK4",
+        "https://www.youtube.com/watch?v=VL5M5ZihJK4",
+    ],
+)
+demo.launch(share=True)

functions/model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af590bbc6d50b5ca00d2f7cdca06d2e6c8ef94dd6e09019c69b75e816ca5d05
+size 3977504

functions/model_infer.py

@@ -0,0 +1,41 @@
+from keras.preprocessing.sequence import pad_sequences
+import re
+
+# import tensorflow as tf
+import os
+import requests
+from keras.models import load_model
+
+headers = {"Authorization": f"Bearer {os.environ['HF_Token']}"}
+
+model = load_model("./RNN_model.keras")
+
+
+def query_embeddings(texts):
+    payload = {"inputs": texts, "options": {"wait_for_model": True}}
+
+    model_id = "sentence-transformers/sentence-t5-base"
+    API_URL = (
+        f"https://api-inference.huggingface.co/pipeline/feature-extraction/{model_id}"
+    )
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
+
+
+def preprocess(sentences):
+    max_len = 1682
+    embeddings = query_embeddings(sentences)
+
+    if len(sentences) > max_len:
+        X = embeddings[:max_len]
+    else:
+        X = embeddings
+    X_padded = pad_sequences([X], maxlen=max_len, dtype="float32", padding="post")
+    return X_padded
+
+
+def predict_from_document(sentences):
+    preprop = preprocess(sentences)
+    prediction = model.predict(preprop)
+    output = (prediction.flatten()[: len(sentences)] >= 0.5).astype(int)
+    return output

functions/punctuation.py

@@ -0,0 +1,58 @@
+import requests
+from youtube_transcript_api import YouTubeTranscriptApi
+import json
+import os
+
+headers = {
+    "Authorization": f"Bearer {os.environ['HF_Token']}"
+}  # NOTE: put this somewhere else
+
+
+def retrieve_transcript(vid_id):
+    try:
+        transcript = YouTubeTranscriptApi.get_transcript(vid_id)
+        return transcript
+    except Exception as e:
+        return None
+
+
+def split_transcript(transcript, chunk_size=40):
+    sentences = []
+    for i in range(0, len(transcript), chunk_size):
+        to_add = [x["text"] for x in transcript[i : i + chunk_size]]
+        sentences.append(" ".join(to_add))
+    return sentences
+
+
+def query_punctuation(splits):
+    payload = {"inputs": splits}
+    API_URL = "https://api-inference.huggingface.co/models/oliverguhr/fullstop-punctuation-multilang-large"
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
+
+
+def parse_output(output, comb):
+    total = []
+
+    # loop over the response from the huggingface api
+    for i, o in enumerate(output):
+        added = 0
+        tt = comb[i]
+        for elem in o:
+            # Loop over the output chunks and add the . and ?
+            if elem["entity_group"] not in ["0", ",", ""]:
+                split = elem["end"] + added
+                tt = tt[:split] + elem["entity_group"] + tt[split:]
+                added += 1
+        total.append(tt)
+    return " ".join(total)
+
+
+def punctuate(video_id):
+    transcript = retrieve_transcript(video_id)
+    splits = split_transcript(
+        transcript
+    )  # Get the transcript from the YoutubeTranscriptApi
+    resp = query_punctuation(splits)  # Get the response from the Inference API
+    punctuated_transcript = parse_output(resp, splits)
+    return punctuated_transcript

model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af590bbc6d50b5ca00d2f7cdca06d2e6c8ef94dd6e09019c69b75e816ca5d05
+size 3977504

requirements.txt

@@ -0,0 +1,4 @@
+youtube_transcript_api
+tensorflow==2.15
+keras
+keras-nlp