Upload folder using huggingface_hub

.gitattributes

@@ -1,34 +1,28 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
 *.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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/kirsten_dunst.wav filter=lfs diff=lfs merge=lfs -text

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install https://gradio-builds.s3.amazonaws.com/c0138fa3cf227b01cdc468c7817298d5f7849c9e/gradio-3.32.0-py3-none-any.whl
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

README.md

@@ -1,12 +1,7 @@
 ---
-title: Same Test
-emoji: 🌖
-colorFrom: yellow
-colorTo: red
+title: same-test
+app_file: app.py
 sdk: gradio
 sdk_version: 3.32.0
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+test readme

app.py

@@ -0,0 +1,108 @@
+import gradio as gr
+import torch
+from torchaudio.sox_effects import apply_effects_file
+from transformers import AutoFeatureExtractor, AutoModelForAudioXVector
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+OUTPUT_OK = (
+    """
+    <div class="container">
+        <div class="row"><h1 style="text-align: center">The speakers are</h1></div>
+        <div class="row"><h1 class="display-1 text-success" style="text-align: center">{:.1f}%</h1></div>
+        <div class="row"><h1 style="text-align: center">similar</h1></div>
+        <div class="row"><h1 class="text-success" style="text-align: center">Welcome, human!</h1></div>
+        <div class="row"><small style="text-align: center">(You must get at least 85% to be considered the same person)</small><div class="row">
+    </div>
+"""
+)
+OUTPUT_FAIL = (
+    """
+    <div class="container">
+        <div class="row"><h1 style="text-align: center">The speakers are</h1></div>
+        <div class="row"><h1 class="display-1 text-danger" style="text-align: center">{:.1f}%</h1></div>
+        <div class="row"><h1 style="text-align: center">similar</h1></div>
+        <div class="row"><h1 class="text-danger" style="text-align: center">You shall not pass!</h1></div>
+        <div class="row"><small style="text-align: center">(You must get at least 85% to be considered the same person)</small><div class="row">
+    </div>
+"""
+)
+
+EFFECTS = [
+    ["remix", "-"],
+    ["channels", "1"],
+    ["rate", "16000"],
+    ["gain", "-1.0"],
+    ["silence", "1", "0.1", "0.1%", "-1", "0.1", "0.1%"],
+    ["trim", "0", "10"],
+]
+
+THRESHOLD = 0.85
+
+model_name = "microsoft/unispeech-sat-base-plus-sv"
+feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+model = AutoModelForAudioXVector.from_pretrained(model_name).to(device)
+cosine_sim = torch.nn.CosineSimilarity(dim=-1)
+
+
+def similarity_fn(path1, path2):
+    if not (path1 and path2):
+        return '<b style="color:red">ERROR: Please record audio for *both* speakers!</b>'
+
+    wav1, _ = apply_effects_file(path1, EFFECTS)
+    wav2, _ = apply_effects_file(path2, EFFECTS)
+    print(wav1.shape, wav2.shape)
+
+    input1 = feature_extractor(wav1.squeeze(0), return_tensors="pt", sampling_rate=16000).input_values.to(device)
+    input2 = feature_extractor(wav2.squeeze(0), return_tensors="pt", sampling_rate=16000).input_values.to(device)
+
+    with torch.no_grad():
+        emb1 = model(input1).embeddings
+        emb2 = model(input2).embeddings
+    emb1 = torch.nn.functional.normalize(emb1, dim=-1).cpu()
+    emb2 = torch.nn.functional.normalize(emb2, dim=-1).cpu()
+    similarity = cosine_sim(emb1, emb2).numpy()[0]
+
+    if similarity >= THRESHOLD:
+        output = OUTPUT_OK.format(similarity * 100)
+    else:
+        output = OUTPUT_FAIL.format(similarity * 100)
+
+    return output
+
+
+inputs = [
+    gr.inputs.Audio(source="microphone", type="filepath", optional=True, label="Speaker #1"),
+    gr.inputs.Audio(source="microphone", type="filepath", optional=True, label="Speaker #2"),
+]
+output = gr.outputs.HTML(label="")
+
+
+description = (
+    "This demo from Microsoft will compare two speech samples and determine if they are from the same speaker. "
+    "Try it with your own voice!"
+)
+article = (
+    "<p style='text-align: center'>"
+    "<a href='https://huggingface.co/microsoft/unispeech-sat-large-sv' target='_blank'>🎙️ Learn more about UniSpeech-SAT</a> | "
+    "<a href='https://arxiv.org/abs/2110.05752' target='_blank'>📚 UniSpeech-SAT paper</a> | "
+    "<a href='https://www.danielpovey.com/files/2018_icassp_xvectors.pdf' target='_blank'>📚 X-Vector paper</a>"
+    "</p>"
+)
+examples = [
+    ["samples/cate_blanch.mp3", "samples/cate_blanch_2.mp3"],
+    ["samples/cate_blanch.mp3", "samples/kirsten_dunst.wav"],
+]
+
+interface = gr.Interface(
+    fn=similarity_fn,
+    inputs=inputs,
+    outputs=output,
+    description=description,
+    layout="horizontal",
+    theme="huggingface",
+    allow_flagging=False,
+    live=False,
+    examples=examples,
+)
+interface.launch(enable_queue=True)

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/huggingface/transformers
+torchaudio

samples/kirsten_dunst.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab77b27959f0f43126c94c4de3baa23b3f92c3c2e26ba322af2d6cd688f3233
+size 1287798