Duplicate from camenduru/one-shot-talking-face

Co-authored-by: camenduru <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+*.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
+examples/obama2.wav filter=lfs diff=lfs merge=lfs -text
+examples/trump.wav filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,35 @@
+# https://gitlab.com/nvidia/container-images/cuda/-/blob/master/dist/11.2.1/ubuntu2004/devel/cudnn8/Dockerfile
+FROM nvidia/cuda:11.2.1-cudnn8-devel-ubuntu20.04
+ENV DEBIAN_FRONTEND noninteractive
+
+WORKDIR /content
+RUN apt-get update -y && apt-get upgrade -y && apt-get install -y sudo && apt-get install -y python3-pip && pip3 install --upgrade pip
+RUN apt-get install -y gnupg wget htop sudo git git-lfs software-properties-common build-essential cmake curl
+RUN apt-get install -y ffmpeg libavcodec-dev libavformat-dev libavdevice-dev libgl1 libgtk2.0-0 jq libdc1394-22-dev libraw1394-dev libopenblas-base
+
+ENV PATH="/home/admin/.local/bin:${PATH}"
+
+RUN pip3 install pandas scipy matplotlib torch torchvision torchaudio gradio altair imageio-ffmpeg pocketsphinx jq "numpy<1.24"
+
+RUN git lfs install
+RUN git clone https://huggingface.co/camenduru/pocketsphinx-20.04-t4 pocketsphinx && cd pocketsphinx && cmake --build build --target install
+
+RUN git clone https://huggingface.co/camenduru/one-shot-talking-face-20.04-t4 one-shot-talking-face && cd one-shot-talking-face && pip install -r requirements.txt && chmod 755 OpenFace/FeatureExtraction
+RUN mkdir /content/out
+
+COPY app.py /content/app.py
+COPY examples /content/examples
+
+RUN adduser --disabled-password --gecos '' admin
+RUN adduser admin sudo
+RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+
+RUN chown -R admin:admin /content
+RUN chmod -R 777 /content
+RUN chown -R admin:admin /home
+RUN chmod -R 777 /home
+USER admin
+
+EXPOSE 7860
+
+CMD ["python3", "app.py"]

README.md

@@ -0,0 +1,11 @@
+---
+title: One Shot Talking Face
+emoji: 🌞
+colorFrom: blue
+colorTo: blue
+sdk: docker
+sdk_version: 3.9
+app_file: oh-no.py
+pinned: false
+duplicated_from: camenduru/one-shot-talking-face
+---

app.py

@@ -0,0 +1,66 @@
+import gradio as gr
+import os, subprocess, torchaudio
+import torch
+from PIL import Image
+
+block = gr.Blocks()
+
+def pad_image(image):
+    w, h = image.size
+    if w == h:
+        return image
+    elif w > h:
+        new_image = Image.new(image.mode, (w, w), (0, 0, 0))
+        new_image.paste(image, (0, (w - h) // 2))
+        return new_image
+    else:
+        new_image = Image.new(image.mode, (h, h), (0, 0, 0))
+        new_image.paste(image, ((h - w) // 2, 0))
+        return new_image
+
+def calculate(image_in, audio_in):
+    waveform, sample_rate = torchaudio.load(audio_in)
+    waveform = torch.mean(waveform, dim=0, keepdim=True)
+    torchaudio.save("/content/audio.wav", waveform, sample_rate, encoding="PCM_S", bits_per_sample=16)
+    image = Image.open(image_in)
+    image = pad_image(image)
+    image.save("image.png")
+
+    pocketsphinx_run = subprocess.run(['pocketsphinx', '-phone_align', 'yes', 'single', '/content/audio.wav'], check=True, capture_output=True)
+    jq_run = subprocess.run(['jq', '[.w[]|{word: (.t | ascii_upcase | sub("<S>"; "sil") | sub("<SIL>"; "sil") | sub("\\\(2\\\)"; "") | sub("\\\(3\\\)"; "") | sub("\\\(4\\\)"; "") | sub("\\\[SPEECH\\\]"; "SIL") | sub("\\\[NOISE\\\]"; "SIL")), phones: [.w[]|{ph: .t | sub("\\\+SPN\\\+"; "SIL") | sub("\\\+NSN\\\+"; "SIL"), bg: (.b*100)|floor, ed: (.b*100+.d*100)|floor}]}]'], input=pocketsphinx_run.stdout, capture_output=True)
+    with open("test.json", "w") as f:
+        f.write(jq_run.stdout.decode('utf-8').strip())
+
+    os.system(f"cd /content/one-shot-talking-face && python3 -B test_script.py --img_path /content/image.png --audio_path /content/audio.wav --phoneme_path /content/test.json --save_dir /content/train")
+    return "/content/train/image_audio.mp4"
+    
+def run():
+  with block:
+    gr.Markdown(
+    """
+    <style> body { text-align: right} </style>
+    map: 📄 [arxiv](https://arxiv.org/abs/2112.02749) &nbsp; ⇨ 👩‍💻 [github](https://github.com/FuxiVirtualHuman/AAAI22-one-shot-talking-face) &nbsp; ⇨ 🦒 [colab](https://github.com/camenduru/one-shot-talking-face-colab) &nbsp; ⇨ 🤗 [huggingface](https://huggingface.co/spaces/camenduru/one-shot-talking-face) &nbsp; | &nbsp; tools: 🌀 [duplicate this space](https://huggingface.co/spaces/camenduru/sandbox?duplicate=true) &nbsp; | 🐢 [tortoise tts](https://huggingface.co/spaces/mdnestor/tortoise) &nbsp; | 🎨 [text-to-image](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) &nbsp; | 🐣 [twitter](https://twitter.com/camenduru) &nbsp;
+    """)
+    with gr.Group():
+      with gr.Box():
+        with gr.Row().style(equal_height=True):
+          image_in = gr.Image(show_label=False, type="filepath")
+          audio_in = gr.Audio(show_label=False, type='filepath')
+          video_out = gr.Video(show_label=False)
+        with gr.Row().style(equal_height=True):
+          btn = gr.Button("Generate")          
+
+    examples = gr.Examples(examples=[
+      ["./examples/monalisa.jpg", "./examples/obama2.wav"],
+      ["./examples/monalisa.jpg", "./examples/trump.wav"],
+      ["./examples/o2.jpg", "./examples/obama2.wav"],
+      ["./examples/o2.jpg", "./examples/trump.wav" ],
+      ["./examples/image.png", "./examples/audio.wav"],
+    ], fn=calculate, inputs=[image_in, audio_in], outputs=[video_out], cache_examples=True)
+
+    btn.click(calculate, inputs=[image_in, audio_in], outputs=[video_out])
+    block.queue()
+    block.launch(server_name="0.0.0.0", server_port=7860)
+
+if __name__ == "__main__":
+    run()

examples/obama2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d59c8e469bda05ae7a7435420322c8a192b75ab44e7dc694a81b81512a36542
+size 1280078

examples/trump.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb718f7537230f1c8a24fae2ec28eb56381f20ce25140d0b16a4dd1873de5a86
+size 1856140

oh-no.py

@@ -0,0 +1,14 @@
+import gradio as gr
+
+block = gr.Blocks()
+
+def run():
+  with block:
+    gr.Markdown(
+    """
+    <p>oh no 😐 something wrong with the 🤗 hugging face servers 😐 hopefully, it will be fixed soon</p>
+    """)
+    block.launch(server_name="0.0.0.0", server_port=7860)
+
+if __name__ == "__main__":
+    run()

test.json

@@ -0,0 +1,977 @@
+[
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 0,
+        "ed": 18
+      }
+    ]
+  },
+  {
+    "word": "I",
+    "phones": [
+      {
+        "ph": "AY",
+        "bg": 18,
+        "ed": 21
+      }
+    ]
+  },
+  {
+    "word": "WANT",
+    "phones": [
+      {
+        "ph": "W",
+        "bg": 21,
+        "ed": 33
+      },
+      {
+        "ph": "AO",
+        "bg": 33,
+        "ed": 48
+      },
+      {
+        "ph": "N",
+        "bg": 48,
+        "ed": 60
+      },
+      {
+        "ph": "T",
+        "bg": 60,
+        "ed": 65
+      }
+    ]
+  },
+  {
+    "word": "TO",
+    "phones": [
+      {
+        "ph": "T",
+        "bg": 65,
+        "ed": 74
+      },
+      {
+        "ph": "UW",
+        "bg": 74,
+        "ed": 80
+      }
+    ]
+  },
+  {
+    "word": "LOSE",
+    "phones": [
+      {
+        "ph": "L",
+        "bg": 80,
+        "ed": 87
+      },
+      {
+        "ph": "UW",
+        "bg": 87,
+        "ed": 121
+      },
+      {
+        "ph": "Z",
+        "bg": 121,
+        "ed": 150
+      }
+    ]
+  },
+  {
+    "word": "SIL",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 150,
+        "ed": 158
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 158,
+        "ed": 250
+      }
+    ]
+  },
+  {
+    "word": "TO",
+    "phones": [
+      {
+        "ph": "T",
+        "bg": 250,
+        "ed": 255
+      },
+      {
+        "ph": "UW",
+        "bg": 254,
+        "ed": 276
+      }
+    ]
+  },
+  {
+    "word": "TO",
+    "phones": [
+      {
+        "ph": "T",
+        "bg": 276,
+        "ed": 302
+      },
+      {
+        "ph": "AH",
+        "bg": 302,
+        "ed": 328
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 328,
+        "ed": 337
+      }
+    ]
+  },
+  {
+    "word": "KEEP",
+    "phones": [
+      {
+        "ph": "K",
+        "bg": 337,
+        "ed": 364
+      },
+      {
+        "ph": "IY",
+        "bg": 364,
+        "ed": 367
+      },
+      {
+        "ph": "P",
+        "bg": 367,
+        "ed": 375
+      }
+    ]
+  },
+  {
+    "word": "YOU",
+    "phones": [
+      {
+        "ph": "Y",
+        "bg": 375,
+        "ed": 382
+      },
+      {
+        "ph": "UW",
+        "bg": 382,
+        "ed": 385
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 385,
+        "ed": 392
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 392,
+        "ed": 446
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 446,
+        "ed": 475
+      }
+    ]
+  },
+  {
+    "word": "TRUST",
+    "phones": [
+      {
+        "ph": "T",
+        "bg": 475,
+        "ed": 482
+      },
+      {
+        "ph": "R",
+        "bg": 482,
+        "ed": 491
+      },
+      {
+        "ph": "AH",
+        "bg": 491,
+        "ed": 495
+      },
+      {
+        "ph": "S",
+        "bg": 495,
+        "ed": 506
+      },
+      {
+        "ph": "T",
+        "bg": 505,
+        "ed": 516
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 516,
+        "ed": 523
+      }
+    ]
+  },
+  {
+    "word": "GROUP",
+    "phones": [
+      {
+        "ph": "G",
+        "bg": 523,
+        "ed": 529
+      },
+      {
+        "ph": "R",
+        "bg": 529,
+        "ed": 532
+      },
+      {
+        "ph": "UW",
+        "bg": 532,
+        "ed": 546
+      },
+      {
+        "ph": "P",
+        "bg": 546,
+        "ed": 553
+      }
+    ]
+  },
+  {
+    "word": "SCHWARTZ",
+    "phones": [
+      {
+        "ph": "SH",
+        "bg": 553,
+        "ed": 564
+      },
+      {
+        "ph": "W",
+        "bg": 564,
+        "ed": 583
+      },
+      {
+        "ph": "AO",
+        "bg": 583,
+        "ed": 624
+      },
+      {
+        "ph": "R",
+        "bg": 624,
+        "ed": 628
+      },
+      {
+        "ph": "T",
+        "bg": 628,
+        "ed": 636
+      },
+      {
+        "ph": "S",
+        "bg": 636,
+        "ed": 639
+      }
+    ]
+  },
+  {
+    "word": "YOU",
+    "phones": [
+      {
+        "ph": "Y",
+        "bg": 639,
+        "ed": 643
+      },
+      {
+        "ph": "UW",
+        "bg": 643,
+        "ed": 646
+      }
+    ]
+  },
+  {
+    "word": "GO",
+    "phones": [
+      {
+        "ph": "G",
+        "bg": 646,
+        "ed": 660
+      },
+      {
+        "ph": "OW",
+        "bg": 660,
+        "ed": 666
+      }
+    ]
+  },
+  {
+    "word": "ON",
+    "phones": [
+      {
+        "ph": "AO",
+        "bg": 666,
+        "ed": 719
+      },
+      {
+        "ph": "N",
+        "bg": 719,
+        "ed": 725
+      }
+    ]
+  },
+  {
+    "word": "AND",
+    "phones": [
+      {
+        "ph": "AH",
+        "bg": 725,
+        "ed": 728
+      },
+      {
+        "ph": "N",
+        "bg": 728,
+        "ed": 734
+      },
+      {
+        "ph": "D",
+        "bg": 734,
+        "ed": 753
+      }
+    ]
+  },
+  {
+    "word": "RUMORS",
+    "phones": [
+      {
+        "ph": "R",
+        "bg": 753,
+        "ed": 766
+      },
+      {
+        "ph": "UW",
+        "bg": 766,
+        "ed": 787
+      },
+      {
+        "ph": "M",
+        "bg": 787,
+        "ed": 793
+      },
+      {
+        "ph": "ER",
+        "bg": 793,
+        "ed": 797
+      },
+      {
+        "ph": "Z",
+        "bg": 797,
+        "ed": 809
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 809,
+        "ed": 820
+      }
+    ]
+  },
+  {
+    "word": "THAT",
+    "phones": [
+      {
+        "ph": "DH",
+        "bg": 819,
+        "ed": 824
+      },
+      {
+        "ph": "AH",
+        "bg": 825,
+        "ed": 841
+      },
+      {
+        "ph": "T",
+        "bg": 841,
+        "ed": 865
+      }
+    ]
+  },
+  {
+    "word": "WILL",
+    "phones": [
+      {
+        "ph": "W",
+        "bg": 865,
+        "ed": 870
+      },
+      {
+        "ph": "AH",
+        "bg": 869,
+        "ed": 872
+      },
+      {
+        "ph": "L",
+        "bg": 873,
+        "ed": 896
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 896,
+        "ed": 1018
+      }
+    ]
+  },
+  {
+    "word": "REDUCE",
+    "phones": [
+      {
+        "ph": "R",
+        "bg": 1018,
+        "ed": 1023
+      },
+      {
+        "ph": "AH",
+        "bg": 1023,
+        "ed": 1027
+      },
+      {
+        "ph": "D",
+        "bg": 1027,
+        "ed": 1031
+      },
+      {
+        "ph": "UW",
+        "bg": 1031,
+        "ed": 1043
+      },
+      {
+        "ph": "S",
+        "bg": 1043,
+        "ed": 1056
+      }
+    ]
+  },
+  {
+    "word": "THE",
+    "phones": [
+      {
+        "ph": "DH",
+        "bg": 1056,
+        "ed": 1079
+      },
+      {
+        "ph": "AH",
+        "bg": 1079,
+        "ed": 1084
+      }
+    ]
+  },
+  {
+    "word": "DO",
+    "phones": [
+      {
+        "ph": "D",
+        "bg": 1084,
+        "ed": 1087
+      },
+      {
+        "ph": "UW",
+        "bg": 1087,
+        "ed": 1100
+      }
+    ]
+  },
+  {
+    "word": "GET",
+    "phones": [
+      {
+        "ph": "G",
+        "bg": 1100,
+        "ed": 1106
+      },
+      {
+        "ph": "IH",
+        "bg": 1106,
+        "ed": 1112
+      },
+      {
+        "ph": "T",
+        "bg": 1112,
+        "ed": 1118
+      }
+    ]
+  },
+  {
+    "word": "THE",
+    "phones": [
+      {
+        "ph": "DH",
+        "bg": 1118,
+        "ed": 1126
+      },
+      {
+        "ph": "IY",
+        "bg": 1126,
+        "ed": 1130
+      }
+    ]
+  },
+  {
+    "word": "UNIONS",
+    "phones": [
+      {
+        "ph": "Y",
+        "bg": 1130,
+        "ed": 1135
+      },
+      {
+        "ph": "UW",
+        "bg": 1135,
+        "ed": 1150
+      },
+      {
+        "ph": "N",
+        "bg": 1150,
+        "ed": 1153
+      },
+      {
+        "ph": "Y",
+        "bg": 1153,
+        "ed": 1164
+      },
+      {
+        "ph": "AH",
+        "bg": 1164,
+        "ed": 1169
+      },
+      {
+        "ph": "N",
+        "bg": 1169,
+        "ed": 1175
+      },
+      {
+        "ph": "Z",
+        "bg": 1175,
+        "ed": 1205
+      }
+    ]
+  },
+  {
+    "word": "YOUR",
+    "phones": [
+      {
+        "ph": "Y",
+        "bg": 1205,
+        "ed": 1208
+      },
+      {
+        "ph": "UH",
+        "bg": 1208,
+        "ed": 1212
+      },
+      {
+        "ph": "R",
+        "bg": 1212,
+        "ed": 1215
+      }
+    ]
+  },
+  {
+    "word": "OWN",
+    "phones": [
+      {
+        "ph": "OW",
+        "bg": 1215,
+        "ed": 1251
+      },
+      {
+        "ph": "N",
+        "bg": 1251,
+        "ed": 1259
+      }
+    ]
+  },
+  {
+    "word": "COLOR",
+    "phones": [
+      {
+        "ph": "K",
+        "bg": 1259,
+        "ed": 1288
+      },
+      {
+        "ph": "AH",
+        "bg": 1288,
+        "ed": 1291
+      },
+      {
+        "ph": "L",
+        "bg": 1291,
+        "ed": 1301
+      },
+      {
+        "ph": "ER",
+        "bg": 1301,
+        "ed": 1311
+      }
+    ]
+  },
+  {
+    "word": "OR",
+    "phones": [
+      {
+        "ph": "AO",
+        "bg": 1311,
+        "ed": 1328
+      },
+      {
+        "ph": "R",
+        "bg": 1328,
+        "ed": 1332
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1332,
+        "ed": 1335
+      }
+    ]
+  },
+  {
+    "word": "WHAT",
+    "phones": [
+      {
+        "ph": "HH",
+        "bg": 1335,
+        "ed": 1349
+      },
+      {
+        "ph": "W",
+        "bg": 1349,
+        "ed": 1361
+      },
+      {
+        "ph": "AH",
+        "bg": 1361,
+        "ed": 1364
+      },
+      {
+        "ph": "T",
+        "bg": 1364,
+        "ed": 1379
+      }
+    ]
+  },
+  {
+    "word": "WHAT",
+    "phones": [
+      {
+        "ph": "HH",
+        "bg": 1379,
+        "ed": 1387
+      },
+      {
+        "ph": "W",
+        "bg": 1387,
+        "ed": 1390
+      },
+      {
+        "ph": "AH",
+        "bg": 1390,
+        "ed": 1394
+      },
+      {
+        "ph": "T",
+        "bg": 1394,
+        "ed": 1403
+      }
+    ]
+  },
+  {
+    "word": "A",
+    "phones": [
+      {
+        "ph": "EY",
+        "bg": 1403,
+        "ed": 1421
+      }
+    ]
+  },
+  {
+    "word": "SIL",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1421,
+        "ed": 1432
+      }
+    ]
+  },
+  {
+    "word": "BOON",
+    "phones": [
+      {
+        "ph": "B",
+        "bg": 1432,
+        "ed": 1436
+      },
+      {
+        "ph": "UW",
+        "bg": 1436,
+        "ed": 1446
+      },
+      {
+        "ph": "N",
+        "bg": 1446,
+        "ed": 1471
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1471,
+        "ed": 1511
+      }
+    ]
+  },
+  {
+    "word": "FOR",
+    "phones": [
+      {
+        "ph": "F",
+        "bg": 1511,
+        "ed": 1519
+      },
+      {
+        "ph": "R",
+        "bg": 1519,
+        "ed": 1526
+      },
+      {
+        "ph": "ER",
+        "bg": 1526,
+        "ed": 1529
+      }
+    ]
+  },
+  {
+    "word": "LUNCH",
+    "phones": [
+      {
+        "ph": "L",
+        "bg": 1529,
+        "ed": 1537
+      },
+      {
+        "ph": "AH",
+        "bg": 1537,
+        "ed": 1541
+      },
+      {
+        "ph": "N",
+        "bg": 1541,
+        "ed": 1547
+      },
+      {
+        "ph": "CH",
+        "bg": 1547,
+        "ed": 1570
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1570,
+        "ed": 1574
+      }
+    ]
+  },
+  {
+    "word": "THEY",
+    "phones": [
+      {
+        "ph": "DH",
+        "bg": 1574,
+        "ed": 1584
+      },
+      {
+        "ph": "EY",
+        "bg": 1584,
+        "ed": 1610
+      }
+    ]
+  },
+  {
+    "word": "ISSUE",
+    "phones": [
+      {
+        "ph": "IH",
+        "bg": 1610,
+        "ed": 1616
+      },
+      {
+        "ph": "SH",
+        "bg": 1616,
+        "ed": 1641
+      },
+      {
+        "ph": "UW",
+        "bg": 1641,
+        "ed": 1680
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1680,
+        "ed": 1688
+      }
+    ]
+  },
+  {
+    "word": "IS",
+    "phones": [
+      {
+        "ph": "IH",
+        "bg": 1688,
+        "ed": 1695
+      },
+      {
+        "ph": "Z",
+        "bg": 1695,
+        "ed": 1715
+      }
+    ]
+  },
+  {
+    "word": "NOT",
+    "phones": [
+      {
+        "ph": "N",
+        "bg": 1714,
+        "ed": 1725
+      },
+      {
+        "ph": "AA",
+        "bg": 1726,
+        "ed": 1737
+      },
+      {
+        "ph": "T",
+        "bg": 1737,
+        "ed": 1740
+      }
+    ]
+  },
+  {
+    "word": "SURE",
+    "phones": [
+      {
+        "ph": "SH",
+        "bg": 1739,
+        "ed": 1764
+      },
+      {
+        "ph": "UH",
+        "bg": 1764,
+        "ed": 1773
+      },
+      {
+        "ph": "R",
+        "bg": 1773,
+        "ed": 1778
+      }
+    ]
+  },
+  {
+    "word": "WHAT",
+    "phones": [
+      {
+        "ph": "W",
+        "bg": 1779,
+        "ed": 1782
+      },
+      {
+        "ph": "AH",
+        "bg": 1782,
+        "ed": 1786
+      },
+      {
+        "ph": "T",
+        "bg": 1786,
+        "ed": 1828
+      }
+    ]
+  },
+  {
+    "word": "sil",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1828,
+        "ed": 1846
+      }
+    ]
+  },
+  {
+    "word": "</S>",
+    "phones": [
+      {
+        "ph": "SIL",
+        "bg": 1846,
+        "ed": 1900
+      }
+    ]
+  }
+]