Spaces:

suvradip2000
/

ASR

Sleeping

App Files Files Community

suvradip2000 commited on Feb 10, 2024

Commit

0fc56a3

verified ·

1 Parent(s): 4a517e8

Upload 5 files

Browse files

Files changed (5) hide show

Dockerfile +24 -0
index.html +202 -0
main.py +94 -0
requirements.txt +7 -0
run.sh +1 -0

Dockerfile ADDED Viewed

	@@ -0,0 +1,24 @@

+# Use an official Python runtime as a parent image
+FROM python:3.8-slim
+# Set the working directory in the container
+WORKDIR /app
+# Copy the current directory contents into the container at /app
+COPY . /app
+# Install any needed packages specified in requirements.txt
+RUN apt-get update && \
+    apt-get install -y ffmpeg portaudio19-dev && \
+    rm -rf /var/lib/apt/lists/* && \
+    pip install --no-cache-dir -r requirements.txt && \
+    pip install python-multipart
+# Make port 7860 available to the world outside this container
+EXPOSE 7860
+# Define environment variable for FastAPI
+ENV PYTHONUNBUFFERED 1
+# Command to run the application
+CMD ["uvicorn", "soundscripter_fastAPI:app", "--host", "0.0.0.0", "--port", "7860"]

index.html ADDED Viewed

	@@ -0,0 +1,202 @@

+<!DOCTYPE html>
+<html>
+<head>
+  <title>Speech-to-Text Translator</title>
+  <!-- Add Bootstrap CSS link here -->
+  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css">
+  <style>
+    * {
+      margin: 0;
+      padding: 0;
+      box-sizing: border-box;
+    }
+    body {
+      font-family: Arial, sans-serif;
+      background-color: #f8f9fa;
+    }
+    #header {
+      background-color: #4D2B8F;
+      color: #fff;
+      padding: 20px;
+      text-align: center;
+    }
+    #title {
+      font-size: 24px;
+      margin-bottom: 10px;
+    }
+    #subtitle {
+      font-size: 20px;
+      font-weight: 500;
+    }
+    .container {
+      max-width: 600px;
+      margin: 20px auto;
+      background-color: #fff;
+      border-radius: 8px;
+      box-shadow: 0 0 10px rgba(0, 0, 0, 0.2);
+      padding: 20px;
+    }
+    .form-group {
+      margin-bottom: 20px;
+    }
+    .btn {
+      width: 100%;
+      padding: 10px;
+      font-size: 18px;
+      font-weight: bold;
+      border-radius: 5px;
+      cursor: pointer;
+    }
+    #outputText {
+      width: 100%;
+      min-height: 100px;
+      padding: 10px;
+      font-size: 16px;
+      border-radius: 5px;
+      resize: vertical;
+    }
+  </style>
+</head>
+<body>
+  <div id="header">
+    <h1 id="title">Automatic Speech Recognition</h1>
+    <p id="subtitle">Group 27</p>
+  </div>
+<div class="container">
+  <div class="form-group">
+    <label for="audioUpload">Upload Audio File:</label>
+    <input type="file" class="form-control" id="audioUpload">
+  </div>
+  <div class="form-group">
+    <label for="languageSelect">Select Language:</label>
+    <select class="form-control" id="languageSelect">
+      <option value="en">English</option>
+    </select>
+  </div>
+  <div class="form-group">
+    <button class="btn btn-primary" id="recordButton">Start Recording</button>
+    <button class="btn btn-secondary" id="submitButton">Transcribe</button>
+  </div>
+  <div class="form-group">
+    <textarea class="form-control" id="outputText" rows="5" readonly style="display: none;"></textarea>
+  </div>
+</div>
+  <!-- Add Bootstrap JS link and any other required scripts here -->
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.16.0/umd/popper.min.js"></script>
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/js/bootstrap.min.js"></script>
+  <script>
+    let isRecording = false;
+    let recordedChunks = [];
+    let uploadedFile;
+    let recordedAudioBlob;
+    let mediaRecorder;
+    const recordButton = document.getElementById("recordButton");
+    const submitButton = document.getElementById("submitButton");
+    const languageSelect = document.getElementById("languageSelect");
+    const outputText = document.getElementById("outputText");
+    recordButton.addEventListener("click", function () {
+      if (!isRecording) {
+        navigator.mediaDevices.getUserMedia({ audio: true }).then(function (stream) {
+          mediaRecorder = new MediaRecorder(stream);
+          recordedChunks = [];
+          mediaRecorder.ondataavailable = function (e) {
+            recordedChunks.push(e.data);
+          };
+          mediaRecorder.onstop = function () {
+            recordedAudioBlob = new Blob(recordedChunks, { type: "audio/wav" });
+          };
+          mediaRecorder.start();
+          isRecording = true;
+          recordButton.innerText = "Stop Recording";
+        }).catch(function (err) {
+          console.error("Error accessing microphone:", err);
+        });
+      } else {
+        mediaRecorder.stop();
+        isRecording = false;
+        recordButton.innerText = "Start Recording";
+      }
+    });
+    const audioUpload = document.getElementById("audioUpload");
+    audioUpload.addEventListener("change", function (event) {
+      uploadedFile = event.target.files[0];
+      if (uploadedFile) {
+        const fileReader = new FileReader();
+        fileReader.onload = function () {
+          uploadedArrayBuffer = fileReader.result;
+        };
+        fileReader.readAsArrayBuffer(uploadedFile);
+      }
+    });
+    submitButton.addEventListener("click", function () {
+      if (recordedAudioBlob || uploadedFile) {
+        const formData = new FormData();
+        if (recordedAudioBlob) {
+          formData.append("audio", recordedAudioBlob, "recorded_audio.wav");
+        } else if (uploadedFile) {
+          formData.append("audio", uploadedFile, uploadedFile.name);
+        }
+outputText.style.display="block";
+        formData.append("language", languageSelect.value);
+        fetch("/process_audio", {
+          method: "POST",
+          body: formData,
+        })
+          .then((response) => response.json())
+          .then((data) => {
+            if (data.success) {
+              outputText.value = "Translated Text : " + data.language;
+            } else {
+              outputText.value = data.message;
+            }
+          })
+          .catch((error) => {
+            console.error("Error communicating with the backend:", error);
+            outputText.value = "Backend communication failed.";
+          });
+        if (recordedAudioBlob) {
+          const downloadLink = document.createElement("a");
+          downloadLink.href = URL.createObjectURL(recordedAudioBlob);
+          downloadLink.download = "recorded_audio.wav";
+          downloadLink.style.display = "none";
+          document.body.appendChild(downloadLink);
+          downloadLink.click();
+          URL.revokeObjectURL(downloadLink.href);
+          document.body.removeChild(downloadLink);
+        }
+      } else {
+        outputText.value = "Please record audio or upload a file and select a language before submitting.";
+      }
+    });
+  </script>
+</body>
+</html>

main.py ADDED Viewed

	@@ -0,0 +1,94 @@

+import os
+import shutil
+import subprocess
+from fastapi import FastAPI, File, UploadFile, Form
+from fastapi.responses import FileResponse, JSONResponse
+from fastapi.responses import HTMLResponse
+from pydub import AudioSegment
+import shutil
+import tempfile
+import speech_recognition as sr
+import os
+r = sr.Recognizer()
+app = FastAPI()
+def resample_audio(input_path, output_path, target_sample_rate):
+    ffmpeg_cmd = [
+        "ffmpeg",
+        "-i", input_path,
+        "-ar", str(target_sample_rate),
+        output_path
+    ]
+    subprocess.run(ffmpeg_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+@app.get("/", response_class=HTMLResponse)
+async def read_root():
+    # Provide the path to the HTML file containing the front-end code
+    with open("index.html", "r") as file:
+        html_content = file.read()
+    return html_content
+def get_sampling_rate(audio_file_path):
+    audio = AudioSegment.from_file(audio_file_path)
+    return audio.frame_rate
+@app.post("/process_audio")
+async def process_audio(audio: UploadFile = File(...), language: str = Form(...)):
+    if not audio or not language:
+        return JSONResponse(content={"success": False}, status_code=400)
+    # Check if the uploaded file is in WAV format
+    if audio.content_type != "audio/wav":
+        return JSONResponse(content={"success": False, "message": "Audio must be in WAV format."}, status_code=400)
+    try:
+        # Save the received audio to a temporary file
+         with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_file:
+            temp_file_path = temp_file.name
+            shutil.copyfileobj(audio.file, temp_file)
+        # Print the file path for debugging
+         output_path = tempfile.mktemp(suffix=".wav")
+        # Resample the audio to 16000 Hz
+         resample_audio(temp_file_path, output_path, target_sample_rate=16000)
+        # Get the sampling rate of the received audio
+         sampling_rate = get_sampling_rate(output_path)
+        # Resample the audio to 16 kHz if needed
+         if sampling_rate != 16000:
+            return JSONResponse(content={"success": False, "message": "Sample rate is not 16000Hz."}, status_code=500)
+    except Exception as e:
+        print("Error processing audio:", e)
+        return JSONResponse(content={"success": False, "message": "Error processing audio."}, status_code=500)
+    # finally:
+    #     # Cleanup: remove the temporary received audio file
+    #     if os.path.exists(audio_file_path):
+    #         os.remove(audio_file_path)
+    return JSONResponse(content={"success": True, "language":calling_asr(output_path,language)})
+def calling_asr(wav_file,lid):
+    AUDIO_FILE=wav_file
+    # aud_name=AUDIO_FILE.split('/')[-1].split('.')[0]
+    file=open(wav_file+".txt","w")
+    text="cant read wav file"
+    try:
+        with sr.AudioFile(AUDIO_FILE) as source:
+            audio = r.record(source)
+        text = r.recognize_google(audio, language=lid)
+        #file.write(aud_name +"\t"+text)
+        return text
+    except:
+        #file.write(" "+"Error in segement"+" ")
+        return text
+    #file.close()
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt ADDED Viewed

	@@ -0,0 +1,7 @@

+fastapi
+uvicorn
+pydub
+SpeechRecognition
+numpy
+librosa
+sounddevice

run.sh ADDED Viewed

	@@ -0,0 +1 @@


1	+ python -m uvicorn main:app --reload