Add code

README.md

@@ -9,6 +9,8 @@ app_file: app.py
 pinned: false
 license: mit
 short_description: Use Dia tts model through HF Inference
+hf_oauth_scopes:
+ - inference-api
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,61 @@
+import httpx
+
+import gradio as gr
+from gradio_dialogue import Dialogue
+
+emotions = ["(laughs)", "(clears throat)", "(sighs)", "(gasps)", "(coughs)", "(singing)", "(sings)", "(mumbles)", "(beep)", "(groans)", "(sniffs)", "(claps)", "(screams)", "(inhales)", "(exhales)", "(applause)", "(burps)", "(humming)", "(sneezes)", "(chuckle)", "(whistles)"]
+speakers = ["Speaker 1", "Speaker 2"]
+
+client  = httpx.AsyncClient(timeout=180)
+
+
+async def query(dialogue: str, token: gr.OAuthToken | None):
+    if token is None:
+        raise gr.Error("No token provided. Use Sign in with Hugging Face to get a token.")
+    API_URL = "https://router.huggingface.co/fal-ai/fal-ai/dia-tts"
+    headers = {
+        "Authorization": f"Bearer {token.token}",
+    }
+    response = await client.post(API_URL, headers=headers, json={"text": dialogue})
+    url = response.json()["audio"]["url"]
+    print("URL: ", url)
+    return url
+
+def formatter(speaker, text):
+    speaker = speaker.split(" ")[1]
+    return f"[S{speaker}]: {text}"
+
+with gr.Blocks() as demo:
+    with gr.Sidebar():
+        login_button = gr.LoginButton()
+    gr.HTML(
+        """
+        <h1 style='text-align: center; display: flex; align-items: center; justify-content: center;'>
+        <img src=https://cdn-lfs-us-1.hf.co/repos/0f/d0/0fd0968732b9b1a23edbcfa11604db1b053ea9f874bbc66b0aceeab9c5a3c517/0946854c0d2e4813049b21cfb123680dd2cf11b837bda827d75c3c8dec47982b?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27Vibing%252520Huggy.gif%3B+filename%3D%22Vibing%2520Huggy.gif%22%3B&response-content-type=image%2Fgif&Expires=1745535621&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc0NTUzNTYyMX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzBmL2QwLzBmZDA5Njg3MzJiOWIxYTIzZWRiY2ZhMTE2MDRkYjFiMDUzZWE5Zjg3NGJiYzY2YjBhY2VlYWI5YzVhM2M1MTcvMDk0Njg1NGMwZDJlNDgxMzA0OWIyMWNmYjEyMzY4MGRkMmNmMTFiODM3YmRhODI3ZDc1YzNjOGRlYzQ3OTgyYj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=c2qfu6PYMaKDWG8PqF2xpa2p4yPONOOLPlqU%7EUDVFhXCMmXQF3XO7mPSkdBtaEYv-5A4Jwd9y5Qasa%7ECJoVhvdeAefz84v%7ESK0wVVjIBDlrYZoTe4IvQ1H26-i0tKYC-fa6qHZ2Dd5OFZdHvPlhx4tvJBcGB-r0puc2-6TQ85kqre%7EIK%7E6UHaJl8y7Orl4CKlKqir2LKim7ORP2zMLsfrC6j82Fk%7EmJDcsPDxqQ6EPiphRuiHFNI16vDYrGoIH4AXqF6l3tQh8sLbSnKfO-V4DgaoSCM2soxGmvkrN%7EwvB7DzT7ZB%7ENt-rqKKHLlBlHfNLLdBlyMFrnqSBpPAtRrRA__&Key-Pair-Id=K24J24Z295AEI9 alt="Dancing Huggy" style="height: 100px; margin-right: 10px"> Dia Dialogue Generation Model
+        </h1>
+        <h2 style='text-align: center; display: flex; align-items: center; justify-content: center;'>Model by <a href="https://huggingface.co/nari-labs/Dia-1.6B"> Nari Labs</a>. Powered by HF and <a href="https://fal.ai/">Fal AI</a>  API.</h2>
+        <h3>Dia is a dialogue generation model that can generate realistic dialogue between two speakers. Use the dialogue component to create a conversation and then hit the submit button in the bottom right corner to see it come to life .</h3>
+        """
+    )
+    with gr.Row():
+        with gr.Column():
+            dialogue = Dialogue(speakers=speakers, emotions=emotions,
+                                formatter=formatter)
+        with gr.Column():
+            with gr.Row():
+                audio = gr.Audio(label="Audio")
+            with gr.Row():
+                gr.DeepLinkButton(value="Share Audio via Link")
+    with gr.Row():
+        gr.Examples(examples=[
+            [[{"speaker": "Speaker 1", "text": "Why did the chicken cross the road?"},
+             {"speaker": "Speaker 2", "text": "I don't know!"},
+             {"speaker": "Speaker 1", "text": "to get to the other side! (laughs)"}]],
+             [[{"speaker": "Speaker 1", "text": "(sighs) I am a little tired today."},
+             {"speaker": "Speaker 2", "text": "Hang in there!"},
+             ]]], inputs=[dialogue], cache_examples=False)
+
+    dialogue.submit(query, [dialogue], audio)
+
+demo.launch()
+

requirements.txt

@@ -0,0 +1 @@
+gradio-dialogue>=0.0.3