test asr model

README.md

@@ -1,14 +1,13 @@
 ---
-title: Sachi ASR Demo
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
+title: 🗣️Live ASR Speech Recognition Gradio🧠💾 
+emoji: 2-Live🗣️
+colorFrom: purple
+colorTo: red
 sdk: gradio
-sdk_version: 5.0.1
+sdk_version: 3.5
 app_file: app.py
 pinned: false
-license: mit
-short_description: demo sachi
+license: apache-2.0
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,64 +1,99 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+import librosa
+import soundfile
+import whisper
+import tempfile
+import os
+import uuid
+import csv
+from datetime import datetime
+from huggingface_hub import hf_hub_download, Repository
+from transformers import pipeline
 
-"""
-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")
+# Dataset configuration (Change with your Hugging Face details)
+DATASET_REPO_URL = "https://huggingface.co/datasets/awacke1/Sachi_demo_dataset"
+DATASET_REPO_ID = "awacke1/Sachi_demo_dataset"
+DATA_FILENAME = "Sachi_demo_dataset.csv"
+DATA_FILE = os.path.join("data", DATA_FILENAME)
+HF_TOKEN = os.environ.get("HF_TOKEN")
 
+PersistToDataset = False  # Change to True to save output to dataset
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Download the dataset if needed
+if PersistToDataset:
+    try:
+        hf_hub_download(
+            repo_id=DATASET_REPO_ID,
+            filename=DATA_FILENAME,
+            cache_dir="data",
+            force_filename=DATA_FILENAME
+        )
+    except:
+        print("file not found")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    repo = Repository(
+        local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
+    )
 
-    messages.append({"role": "user", "content": message})
+def store_message(name: str, message: str):
+    if name and message:
+        with open(DATA_FILE, "a") as csvfile:
+            writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"])
+            writer.writerow({"name": name.strip(), "message": message.strip(), "time": str(datetime.now())})
+        if PersistToDataset:
+            commit_url = repo.push_to_hub()
+            ret = ""
+            with open(DATA_FILE, "r") as csvfile:
+                reader = csv.DictReader(csvfile)
+                for row in reader:
+                    ret += row
+                    ret += "\r\n"
+    return ret
 
-    response = ""
+# Load Whisper model
+model = whisper.load_model("base")  # You can switch to "small", "medium", or "large" based on your needs
 
-    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
+SAMPLE_RATE = 16000
 
-        response += token
-        yield response
+def process_audio_file(file):
+    data, sr = librosa.load(file, sr=SAMPLE_RATE)
+    data = librosa.to_mono(data)
+    return data
 
+def transcribe(audio, state=""):
+    audio_data = process_audio_file(audio)
+    with tempfile.TemporaryDirectory() as tmpdir:
+        audio_path = os.path.join(tmpdir, f'audio_{uuid.uuid4()}.wav')
+        soundfile.write(audio_path, audio_data, SAMPLE_RATE)
+        
+        # Transcribe audio using Whisper
+        transcriptions = pipe(audio)["text"]
 
-"""
-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)",
-        ),
-    ],
-)
-
+    # Persisting transcription to dataset
+    if PersistToDataset:
+        ret = store_message(transcriptions, state)  # Save to dataset
+        state = state + transcriptions + " " + ret
+    else:
+        state = state + transcriptions
+    
+    return state, state
 
-if __name__ == "__main__":
-    demo.launch()
+gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(source="microphone", type='filepath', streaming=True),
+        "state",
+    ],
+    outputs=[
+        "textbox",
+        "state"
+    ],
+    layout="horizontal",
+    theme="huggingface",
+    title="🗣️ASR-Whisper Live🧠💾",
+    description=f"Live Automatic Speech Recognition (ASR) using Whisper.",
+    allow_flagging='never',
+    live=True,
+    article=f"Result💾 Dataset: [{DATASET_REPO_URL}]({DATASET_REPO_URL})"
+).launch(debug=True)

packages.txt

@@ -0,0 +1,2 @@
+ffmpeg
+libsndfile1

requirements.txt

@@ -1 +1,7 @@
-huggingface_hub==0.25.2
+nemo_toolkit[asr]
+transformers
+torch
+gradio
+Werkzeug
+huggingface_hub
+Pillow