Initial version

app.py

@@ -1,62 +1,85 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+from datasets import load_dataset, Audio
+from transformers import EncodecModel, AutoProcessor
+
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# load a demonstration datasets
+librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# load the model + processor (for pre-processing the audio)
+model = EncodecModel.from_pretrained("facebook/encodec_24khz")
+processor = AutoProcessor.from_pretrained("facebook/encodec_24khz")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# cast the audio data to the correct sampling rate for the model
+librispeech_dummy = librispeech_dummy.cast_column("audio", Audio(sampling_rate=processor.sampling_rate))
+audio_sample = librispeech_dummy[0]["audio"]["array"]
 
-    messages.append({"role": "user", "content": message})
+# pre-process the inputs
+inputs = processor(raw_audio=audio_sample, sampling_rate=processor.sampling_rate, return_tensors="pt")
 
-    response = ""
+# explicitly encode then decode the audio inputs
+encoder_outputs = model.encode(inputs["input_values"], inputs["padding_mask"])
+audio_values = model.decode(encoder_outputs.audio_codes, encoder_outputs.audio_scales, inputs["padding_mask"])[0]
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# or the equivalent with a forward pass
+audio_values = model(inputs["input_values"], inputs["padding_mask"]).audio_values
 
-        response += token
-        yield response
+# def respond(
+#     message,
+#     history: list[tuple[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+# ):
+#     messages = [{"role": "system", "content": system_message}]
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+#     for val in history:
+#         if val[0]:
+#             messages.append({"role": "user", "content": val[0]})
+#         if val[1]:
+#             messages.append({"role": "assistant", "content": val[1]})
+
+#     messages.append({"role": "user", "content": message})
+
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         token = message.choices[0].delta.content
+
+#         response += token
+#         yield response
+
+# """
+# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# """
+# demo = gr.ChatInterface(
+#     respond,
+#     additional_inputs=[
+#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+#         gr.Slider(
+#             minimum=0.1,
+#             maximum=1.0,
+#             value=0.95,
+#             step=0.05,
+#             label="Top-p (nucleus sampling)",
+#         ),
+#     ],
+# )
 
 
 if __name__ == "__main__":