Update app.py

app.py

@@ -1,63 +1,105 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+from transformers import pipeline
+import torch
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+
+classifier = pipeline(
+    "audio-classification", model="MIT/ast-finetuned-speech-commands-v2", device=device
+)
+
+from transformers.pipelines.audio_utils import ffmpeg_microphone_live
+
+
+def launch_fn(
+    wake_word="marvin",
+    prob_threshold=0.5,
+    chunk_length_s=2.0,
+    stream_chunk_s=0.25,
+    debug=False,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    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 wake_word not in classifier.model.config.label2id.keys():
+        raise ValueError(
+            f"Wake word {wake_word} not in set of valid class labels, pick a wake word in the set {classifier.model.config.label2id.keys()}."
+        )
+
+    sampling_rate = classifier.feature_extractor.sampling_rate
+
+    mic = ffmpeg_microphone_live(
+        sampling_rate=sampling_rate,
+        chunk_length_s=chunk_length_s,
+        stream_chunk_s=stream_chunk_s,
+    )
+
+    print("Listening for wake word...")
+    for prediction in classifier(mic):
+        prediction = prediction[0]
+        if debug:
+            print(prediction)
+        if prediction["label"] == wake_word:
+            if prediction["score"] > prob_threshold:
+                return True
+
+transcriber = pipeline(
+    "automatic-speech-recognition", model="openai/whisper-base.en", device=device
 )
+import sys
+
+
+def transcribe(chunk_length_s=5.0, stream_chunk_s=1.0):
+    sampling_rate = transcriber.feature_extractor.sampling_rate
+
+    mic = ffmpeg_microphone_live(
+        sampling_rate=sampling_rate,
+        chunk_length_s=chunk_length_s,
+        stream_chunk_s=stream_chunk_s,
+    )
+
+    print("Start speaking...")
+    for item in transcriber(mic, generate_kwargs={"max_new_tokens": 128}):
+        sys.stdout.write("\033[K")
+        print(item["text"], end="\r")
+        if not item["partial"][0]:
+            break
+
+    return item["text"]
+
+from huggingface_hub import HfFolder
+import requests
+
+
+def query(text, model_id="tiiuae/falcon-7b-instruct"):
+    api_url = f"https://api-inference.huggingface.co/models/{model_id}"
+    headers = {"Authorization": f"Bearer {HfFolder().get_token()}"}
+    payload = {"inputs": text}
+
+    print(f"Querying...: {text}")
+    response = requests.post(api_url, headers=headers, json=payload)
+    return response.json()[0]["generated_text"][len(text) + 1 :]
+
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+
+processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+
+model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts").to(device)
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device)
+
+from datasets import load_dataset
+
+embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+
+def synthesise(text):
+    inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(
+        inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder
+    )
+    return speech.cpu()
 
 
 if __name__ == "__main__":
-    demo.launch()
+    launch_fn()
+    transcription = transcribe()
+    response = query(transcription)
+    audio = synthesise(response)
+    
+    Audio(audio, rate=16000, autoplay=True)