Week 2 Hw

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,10 @@
+---
+title: Text-To-Speech
+emoji: 🎤
+colorFrom: pink
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.18.0
+app_file: app.py
+pinned: false
+---

app.py

@@ -0,0 +1,66 @@
+import gradio as gr
+from gradio_client import Client
+
+def get_speech(text, voice):
+    client = Client("https://collabora-whisperspeech.hf.space/")
+    result = client.predict(
+    		text,	# str  in 'Enter multilingual text💬📝' Textbox component
+    		voice,	# filepath  in 'Upload or Record Speaker Audio (optional)🌬️💬' Audio component
+    		"",	# str  in 'alternatively, you can paste in an audio file URL:' Textbox component
+    		14,	# float (numeric value between 10 and 15) in 'Tempo (in characters per second)' Slider component
+    		api_name="/whisper_speech_demo"
+    )
+    print(result)
+    return result
+
+def get_dreamtalk(image_in, speech):
+    client = Client("https://fffiloni-dreamtalk.hf.space/")
+    result = client.predict(
+    		speech,	# filepath  in 'Audio input' Audio component
+    		image_in,	# filepath  in 'Image' Image component
+    		"M030_front_neutral_level1_001.mat",	# Literal['M030_front_angry_level3_001.mat', 'M030_front_contempt_level3_001.mat', 'M030_front_disgusted_level3_001.mat', 'M030_front_fear_level3_001.mat', 'M030_front_happy_level3_001.mat', 'M030_front_neutral_level1_001.mat', 'M030_front_sad_level3_001.mat', 'M030_front_surprised_level3_001.mat', 'W009_front_angry_level3_001.mat', 'W009_front_contempt_level3_001.mat', 'W009_front_disgusted_level3_001.mat', 'W009_front_fear_level3_001.mat', 'W009_front_happy_level3_001.mat', 'W009_front_neutral_level1_001.mat', 'W009_front_sad_level3_001.mat', 'W009_front_surprised_level3_001.mat', 'W011_front_angry_level3_001.mat', 'W011_front_contempt_level3_001.mat', 'W011_front_disgusted_level3_001.mat', 'W011_front_fear_level3_001.mat', 'W011_front_happy_level3_001.mat', 'W011_front_neutral_level1_001.mat', 'W011_front_sad_level3_001.mat', 'W011_front_surprised_level3_001.mat']  in 'emotional style' Dropdown component
+    		api_name="/infer"
+    )
+    print(result)
+    return result['video']
+
+def pipe (text, voice, image_in):
+
+    speech = get_speech(text, voice)
+    
+    try:
+        video = get_dreamtalk(image_in, speech)
+    except:
+       
+        raise gr.Error('An error occurred while loading DreamTalk: Image may not contain any face')
+
+    return video
+
+with gr.Blocks() as demo:
+    with gr.Column():
+        gr.HTML("""
+        <h2 style="text-align: center;">
+        Text To Video 
+        </h2>
+        <p style="text-align: center;"></p>
+        """)
+        with gr.Row():
+            with gr.Column():
+                image_in = gr.Image(label="Portrait IN", type="filepath", value="https://ibb.co/KK9c5qF")
+            with gr.Column():
+                voice = gr.Audio(type="filepath", label="Upload or Record Speaker audio (Optional voice cloning)")
+                text = gr.Textbox(label="text")
+                submit_btn = gr.Button('Submit')
+            with gr.Column():
+                video_o = gr.Video(label="Video result")
+    submit_btn.click(
+        fn = pipe,
+        inputs = [
+            text, voice, image_in
+        ],
+        outputs = [
+            video_o
+        ],
+        concurrency_limit = 3
+    )
+demo.queue(max_size=10).launch(show_error=True, show_api=False)

d

@@ -0,0 +1,17 @@
+commit 55f9626addc1af2d59d87a32e3a7d4685026713d (HEAD -> main)
+Author: csi-Abil <[email protected]>
+Date:   Fri Feb 23 01:18:48 2024 -0500
+
+    week2 HW
+
+commit 5352e99247879fb2ee69af28670f72ce4e04f900
+Author: csi-Abil <[email protected]>
+Date:   Fri Feb 23 01:13:33 2024 -0500
+
+    Week 2 CTP
+
+commit f4d843f856f21f1f0f64db1a2fe9171646b2cfeb (origin/main, origin/HEAD)
+Author: Abil <[email protected]>
+Date:   Fri Feb 23 05:37:14 2024 +0000
+
+    initial commit