Application files

.env

@@ -0,0 +1,4 @@
+LANGUAGE="uz-UZ"
+SUMMARIZER_MODEL="csebuetnlp/mT5_multilingual_XLSum"
+URL="https://studio.mohir.ai/api/v1/stt"
+API="117a9da1-a2e6-42a8-8e58-408dc3919698:204cd977-922f-41e0-8b7a-203b0ca1c479"

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/STT-project.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,76 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="46">
+            <item index="0" class="java.lang.String" itemvalue="scikit-image" />
+            <item index="1" class="java.lang.String" itemvalue="scipy" />
+            <item index="2" class="java.lang.String" itemvalue="filterpy" />
+            <item index="3" class="java.lang.String" itemvalue="opencv-python" />
+            <item index="4" class="java.lang.String" itemvalue="PyYAML" />
+            <item index="5" class="java.lang.String" itemvalue="torch" />
+            <item index="6" class="java.lang.String" itemvalue="requests" />
+            <item index="7" class="java.lang.String" itemvalue="torchvision" />
+            <item index="8" class="java.lang.String" itemvalue="ultralytics" />
+            <item index="9" class="java.lang.String" itemvalue="tqdm" />
+            <item index="10" class="java.lang.String" itemvalue="hydra-core" />
+            <item index="11" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="12" class="java.lang.String" itemvalue="lap" />
+            <item index="13" class="java.lang.String" itemvalue="Pillow" />
+            <item index="14" class="java.lang.String" itemvalue="networkx" />
+            <item index="15" class="java.lang.String" itemvalue="async-timeout" />
+            <item index="16" class="java.lang.String" itemvalue="Babel" />
+            <item index="17" class="java.lang.String" itemvalue="huggingface-hub" />
+            <item index="18" class="java.lang.String" itemvalue="psycopg2" />
+            <item index="19" class="java.lang.String" itemvalue="MarkupSafe" />
+            <item index="20" class="java.lang.String" itemvalue="numpy" />
+            <item index="21" class="java.lang.String" itemvalue="Jinja2" />
+            <item index="22" class="java.lang.String" itemvalue="frozenlist" />
+            <item index="23" class="java.lang.String" itemvalue="fsspec" />
+            <item index="24" class="java.lang.String" itemvalue="filelock" />
+            <item index="25" class="java.lang.String" itemvalue="certifi" />
+            <item index="26" class="java.lang.String" itemvalue="urllib3" />
+            <item index="27" class="java.lang.String" itemvalue="langid" />
+            <item index="28" class="java.lang.String" itemvalue="sympy" />
+            <item index="29" class="java.lang.String" itemvalue="tokenizers" />
+            <item index="30" class="java.lang.String" itemvalue="transformers" />
+            <item index="31" class="java.lang.String" itemvalue="magic-filter" />
+            <item index="32" class="java.lang.String" itemvalue="aiogram" />
+            <item index="33" class="java.lang.String" itemvalue="packaging" />
+            <item index="34" class="java.lang.String" itemvalue="attrs" />
+            <item index="35" class="java.lang.String" itemvalue="regex" />
+            <item index="36" class="java.lang.String" itemvalue="colorama" />
+            <item index="37" class="java.lang.String" itemvalue="mpmath" />
+            <item index="38" class="java.lang.String" itemvalue="typing_extensions" />
+            <item index="39" class="java.lang.String" itemvalue="charset-normalizer" />
+            <item index="40" class="java.lang.String" itemvalue="aiohttp" />
+            <item index="41" class="java.lang.String" itemvalue="multidict" />
+            <item index="42" class="java.lang.String" itemvalue="yarl" />
+            <item index="43" class="java.lang.String" itemvalue="pytz" />
+            <item index="44" class="java.lang.String" itemvalue="aiosignal" />
+            <item index="45" class="java.lang.String" itemvalue="idna" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N801" />
+          <option value="N802" />
+          <option value="N806" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="int.id" />
+          <option value="datetime.time.__sub__" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/STT-project.iml" filepath="$PROJECT_DIR$/.idea/STT-project.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

app.py

@@ -0,0 +1,17 @@
+import gradio as gr
+from gradio.components import Audio
+from model import STT_with_Summary
+
+output_1 = gr.Textbox(label="STT:")
+output_2 = gr.Textbox(label="Suhbatning qisqacha mazmuni:")
+
+app = gr.Interface(
+    title="Audio xabar va uning qisqacha mazmuni.",
+    fn=STT_with_Summary,
+    inputs=[Audio(source="upload", type="filepath")],
+    outputs=[output_1, output_2],
+    live=False
+)
+
+app.launch(share=False)
+

model.py

@@ -0,0 +1,65 @@
+import subprocess
+
+import speech_recognition as sr
+from transformers import Wav2Vec2FeatureExtractor, Wav2Vec2ForCTC, AutoModelForCTC
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from utils import WHITESPACE_HANDLER
+from transformers import pipeline
+from settings import settings
+from transformers import AutoProcessor, AutoModelForCTC
+import torchaudio
+import requests
+
+
+async def create_wav(audio_file):
+    wav_audio_path = audio_file.replace(audio_file.split(".")[-1], '.wav')
+    subprocess.run(['ffmpeg', '-i', audio_file, wav_audio_path])
+    return wav_audio_path
+
+
+async def speech2text(audio_file):
+    if not audio_file.endswith(".wav"):
+        audio_file = await create_wav()
+
+    # recognizer = sr.Recognizer()
+    # with sr.AudioFile(audio_file) as audio_file:
+    #     audio = recognizer.record(audio_file)
+    #     aligned_transcript = recognizer.recognize_google(audio, language=settings.LANGUAGE)
+
+    url = settings.URL
+    headers = {'Authorization': settings.API}
+    files = {'file': (audio_file, open(audio_file, 'rb'))}
+    response = requests.post(url, headers=headers, files=files)
+    aligned_transcript = response.json()['result']["text"]
+
+    return aligned_transcript
+
+async def summerizer(aligned_transcript):
+    model_name = settings.SUMMARIZER_MODEL
+    tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+    input_ids = tokenizer(
+        [WHITESPACE_HANDLER(aligned_transcript)],
+        return_tensors="pt",
+        padding="max_length",
+        truncation=True,
+        max_length=512)["input_ids"]
+    output_ids = model.generate(
+        input_ids=input_ids,
+        max_length=84,
+        no_repeat_ngram_size=2,
+        num_beams=4
+    )[0]
+    summary = tokenizer.decode(
+        output_ids,
+        skip_special_tokens=True,
+        clean_up_tokenization_spaces=False
+    )
+    return summary
+
+
+async def STT_with_Summary(audio_file):
+    aligned_transcript = await speech2text(audio_file)
+    summary = await summerizer(aligned_transcript)
+    return aligned_transcript, summary

settings.py

@@ -0,0 +1,13 @@
+from pydantic import BaseSettings
+
+class Settings(BaseSettings):
+    LANGUAGE: str
+    SUMMARIZER_MODEL: str
+    URL: str
+    API: str
+
+    class Config:
+        env_file = ".env"
+
+
+settings = Settings()

utils.py

@@ -0,0 +1,3 @@
+import re
+
+WHITESPACE_HANDLER = lambda k: re.sub('\s+', ' ', re.sub('\n+', ' ', k.strip()))