firest commit

.gitignore

@@ -0,0 +1 @@
+WSL

config.py

@@ -0,0 +1,19 @@
+"""
+Author: Tanmay Jain
+Email: csetanmayjain@gmail.com
+"""
+import os
+import subprocess
+
+
+upload_files_path = '/home/akshat/v1/dependency/audio_logs'
+
+hi_am_model_path = "./hi_am_model"
+
+en_am_model_path = "./en_am_model"
+
+        
+
+# upload_files_path = '/home/tanmay/zb/docker_files_donot_delete/v1/audio_logs'
+# hi_am_model_path = "/home/tanmay/zb/Conformer-CTC-BPE-Large.nemo"
+# en_am_model_path = "/home/tanmay/zb/Conformer-CTC-BPE-Large.nemo"

dependency/audio_logs/english/00e6a918-780f-4781-a015-b91a326c64d9/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/06308abc-142a-444c-863c-46a84a6adc0c/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/153dadc1-1ee7-4b46-b76f-62a415aa1dc8/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/2c6e8916-012f-44d3-8e0a-cea7f40ff8f5/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/2fd17592-cc9e-433b-83a5-8e64fcd98715/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/3cf9bb5f-51f8-4d95-ac99-f11920fc6c9d/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/41751b79-03c7-4dea-8f2e-4aa6da74d647/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/495c7c6c-a18d-48f5-a597-16389c1d366c/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/4ee9a133-4b38-424b-9561-5c870c723d50/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/54645247-f260-42f9-b475-d890bd0f5e00/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/61ca0ac4-72f7-4a5c-b82a-02327710d4ce/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/716694d5-64ff-42ac-90dd-b259e40d2ec2/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/95396c57-c169-4f8d-bd8b-124f4224676a/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/DemoTranscript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/be445b40-f504-4ffe-9b36-0da83e312f15/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/c75ea509-a258-423d-845b-4daf922d38ba/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/d1bb4f14-e186-40bd-96bb-a3347f6179d1/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/dc6cc1a6-c3da-4fc1-a79d-1482acf8f993/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/e03026bb-412b-48ac-ba17-52402ee25a4e/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/f2aed9e2-e2a7-4aae-b4a8-24d7b2487704/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/f3264a23-1bba-44e6-a03c-8ce3515a040f/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/english/fa344aa0-9a59-48b0-b360-fe95280bdc59/transcript.txt

@@ -0,0 +1 @@
+well i dont wish to see it anymre observed f b turning away her eyes it is certainly very like old portrad

dependency/audio_logs/hindi/fe00b82d-c412-4537-b81e-1ff45e21b042/transcript.txt

@@ -0,0 +1 @@
+वेलेश  सी एनीोर

requirements.txt

@@ -0,0 +1,204 @@
+absl-py==2.1.0
+aiohttp==3.9.3
+aioice==0.9.0
+aiortc==1.8.0
+aiosignal==1.3.1
+alembic==1.13.1
+altair==5.2.0
+annotated-types==0.6.0
+antlr4-python3-runtime==4.9.3
+asteroid-filterbanks==0.4.0
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==23.2.0
+audioread==3.0.1
+av==11.0.0
+blinker==1.7.0
+braceexpand==0.1.7
+cachetools==5.3.3
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+colorlog==6.8.2
+contourpy==1.2.0
+cryptography==42.0.5
+cycler==0.12.1
+Cython
+cytoolz==0.12.3
+datasets==2.18.0
+decorator==5.1.1
+dill==0.3.8
+dnspython==2.6.1
+docopt==0.6.2
+editdistance==0.8.1
+einops==0.7.0
+exceptiongroup==1.2.0
+executing==2.0.1
+filelock==3.13.1
+Flask==3.0.2
+Flask-Cors==4.0.0
+fonttools==4.49.0
+frozenlist==1.4.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.42
+google-crc32c==1.5.0
+greenlet==3.0.3
+grpcio==1.62.1
+huggingface-hub==0.21.4
+hydra-core==1.3.2
+HyperPyYAML==1.2.2
+idna==3.6
+ifaddr==0.2.0
+inflect==7.0.0
+intervaltree==3.1.0
+ipython
+itsdangerous==2.1.2
+jedi==0.19.1
+Jinja2==3.1.3
+jiwer==3.0.3
+joblib==1.3.2
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+julius==0.2.7
+kaldi-io==0.9.8
+kiwisolver==1.4.5
+lazy_loader==0.3
+lhotse==1.22.0
+librosa==0.10.1
+lightning==2.2.1
+lightning-utilities==0.10.1
+lilcom==1.7
+llvmlite==0.42.0
+Mako==1.3.2
+Markdown==3.5.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.1
+matplotlib==3.8.3
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.0.8
+multidict==6.0.5
+multiprocess==0.70.16
+nemo-asr==0.9.0
+nemo_toolkit==1.23.0
+networkx==3.2.1
+num2words==0.5.13
+numba==0.59.0
+numpy==1.26.4
+# nvidia-cublas-cu12==12.1.3.1
+# nvidia-cuda-cupti-cu12==12.1.105
+# nvidia-cuda-nvrtc-cu12==12.1.105
+# nvidia-cuda-runtime-cu12==12.1.105
+# nvidia-cudnn-cu12==8.9.2.26
+# nvidia-cufft-cu12==11.0.2.54
+# nvidia-curand-cu12==10.3.2.106
+# nvidia-cusolver-cu12==11.4.5.107
+# nvidia-cusparse-cu12==12.1.0.106
+# nvidia-nccl-cu12==2.19.3
+# nvidia-nvjitlink-cu12==12.4.99
+# nvidia-nvtx-cu12==12.1.105
+omegaconf==2.3.0
+onnx==1.15.0
+optuna==3.5.0
+packaging==23.2
+pandas==2.2.1
+parso==0.8.3
+pexpect==4.9.0
+pillow==10.2.0
+platformdirs==4.2.0
+pooch==1.8.1
+primePy==1.3
+prompt-toolkit==3.0.43
+protobuf==4.25.3
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyannote.audio==3.1.1
+pyannote.core==5.0.0
+pyannote.database==5.0.1
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pyarrow==15.0.1
+pyarrow-hotfix==0.6
+pycparser==2.21
+pydantic==2.6.3
+pydantic_core==2.16.3
+pydeck==0.8.1b0
+pydub==0.25.1
+pyee==11.1.0
+Pygments==2.17.2
+pylibsrtp==0.10.0
+pyOpenSSL==24.1.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+pytorch-lightning==2.2.1
+pytorch-metric-learning==2.4.1
+pytz==2024.1
+PyYAML==6.0.1
+rapidfuzz==3.6.2
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruamel.yaml==0.18.6
+ruamel.yaml.clib==0.2.8
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+semver==3.0.2
+sentencepiece==0.2.0
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sortedcontainers==2.4.0
+sounddevice==0.4.6
+soundfile==0.12.1
+sox==1.4.1
+soxr==0.3.7
+speechbrain==1.0.0
+SQLAlchemy==2.0.28
+stack-data==0.6.3
+streamlit==1.32.1
+streamlit-audiorec==0.1.3
+streamlit-webrtc==0.47.6
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.3
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+tensorboardX==2.6.2.2
+text-unidecode==1.3
+threadpoolctl==3.3.0
+tokenizers==0.15.2
+toml==0.10.2
+toolz==0.12.1
+# torch==2.2.1
+# torch-audiomentations==0.11.1
+# torch-pitch-shift==1.2.4
+# torch-stft==0.1.4
+# torchaudio==2.2.1
+# torchmetrics==1.3.1
+tornado==6.4
+tqdm==4.66.2
+traitlets==5.14.1
+transformers==4.38.2
+triton==2.2.0
+typer==0.9.0
+typing_extensions==4.10.0
+tzdata==2024.1
+Unidecode==1.3.8
+urllib3==2.2.1
+watchdog==4.0.0
+wcwidth==0.2.13
+webdataset==0.2.86
+Werkzeug==3.0.1
+wget==3.2
+wrapt==1.16.0
+xxhash==3.4.1
+yarl==1.9.4
+youtokentome

server.py

@@ -0,0 +1,133 @@
+"""
+Author: Tanmay Jain
+Email: csetanmayjain@gmail.com
+"""
+
+import os
+import threading
+import uuid
+
+from flask import Flask, jsonify, request, send_file
+from flask_cors import CORS
+import nemo.collections.asr as nemo_asr
+import subprocess
+import config
+
+
+hi_asr_model = None
+en_asr_model = None
+en_upload_files_path=None
+hi_upload_files_path=None
+def initialize_path():
+
+    global hi_upload_files_path, en_upload_files_path, hi_am_model_path, en_am_model_path
+
+    hi_am_model_path = config.hi_am_model_path
+    en_am_model_path = config.en_am_model_path    
+    hi_upload_files_path = os.path.join(config.upload_files_path, "hindi")
+    en_upload_files_path = os.path.join(config.upload_files_path, "english")
+
+    os.makedirs(hi_upload_files_path, exist_ok=True)
+    os.makedirs(en_upload_files_path, exist_ok=True)
+ 
+
+def load_model(lang):
+
+    global hi_asr_model, en_asr_model
+
+
+    if lang == "hi" and hi_asr_model == None:
+        print("Loading Hindi Model")
+        if not  os.path.exists(hi_am_model_path):
+            download=subprocess.run(["wget","-P",hi_am_model_path,"https://storage.googleapis.com/vakyansh-open-models/conformer_models/hindi/filtered_v1_ssl_2022-07-08_19-43-25/Conformer-CTC-BPE-Large.nemo"],capture_output=True, text=True)
+            print('done Downloading hindi asr')
+        if download.returncode != 0:
+                raise Exception(f"wget download failed: {download.stderr}")
+
+
+      
+            
+
+        #hi_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from(hi_am_model_path)    
+        # path for hi_asr_model for local sever running
+        hi_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from('./hi_am_model/Conformer-CTC-BPE-Large.nemo')
+    if lang == "en" and en_asr_model == None:
+       
+        if not os.path.exists(en_am_model_path):
+            print(en_am_model_path)
+            print('not found downloading english model')
+            download=subprocess.run(["wget","-P",en_am_model_path,"https://storage.googleapis.com/vakyansh-open-models/conformer_models/english/2022-09-13_15-50-48/Conformer-CTC-BPE-Large.nemo"],capture_output=True, text=True)
+            print('done Downloading')
+        print("Loading English Model")
+        
+
+        
+        en_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from('./en_am_model/Conformer-CTC-BPE-Large.nemo')    
+
+
+def transcribe(audio_file_path, transcription_file_path, lang, logprobs=False):
+    
+    #load_model(lang)   
+    if lang == "hi":
+        transcription = hi_asr_model.transcribe([audio_file_path], logprobs=logprobs)[0]
+    if lang == "en":
+        transcription = en_asr_model.transcribe([audio_file_path], logprobs=logprobs)[0]
+
+    f = open(transcription_file_path, "w")
+    f.write(transcription)
+    f.close()
+
+def asr(audio_file_path,lang):
+    initialize_path()
+  
+    global en_upload_files_path,hi_upload_files_path
+    if lang == None:
+        return jsonify({'error': 'no language code provided'}), 400
+    if lang != "hi" and lang != "en":
+        return jsonify({'error': 'Invalid language code'}), 400
+    client_id = str(uuid.uuid4()) 
+
+    if lang == "hi":
+        client_id_dir = os.path.join(hi_upload_files_path, client_id)
+    if lang == "en":
+        client_id_dir = os.path.join(en_upload_files_path, client_id)
+
+
+    transcription_file_path = os.path.join(client_id_dir, "transcript.txt")
+
+    os.makedirs(client_id_dir)
+
+    transcribe(audio_file_path,transcription_file_path,lang)
+    return client_id
+  
+def get_transcription(client_id,lang):
+
+    global en_upload_files_path
+    if client_id == None:
+        return  'No Client ID Provided'
+    if lang == None:
+        return  'no language code provided'
+    if lang != "hi" and lang != "en":
+        return  'Invalid language code'
+    print(type(lang),en_upload_files_path,"PATHS is thisss eherreb")
+    if lang == "hi":
+        print('looking in hindi file path')
+        client_dir = os.path.join('dependency/audio_logs/hindi', client_id)
+    if lang == "en":
+        print('looking in english file path')
+        client_dir = os.path.join('dependency/audio_logs/english', client_id)
+    transcript_file_path = os.path.join(client_dir,'transcript.txt')
+    if not os.path.exists(client_dir):
+        return "Invalid Client ID"
+    if os.path.exists(transcript_file_path):
+        print(transcript_file_path,"transcript file path")
+        #return send_file(transcript_file_path, as_attachment=True, download_name='transcript.txt'), 201
+        return transcript_file_path
+    else:
+        return 'your transcription file is not ready'
+ 
+
+    
+# if __name__ == '__main__':
+#     initialize_path()
+#     app.run(host='0.0.0.0', port=5000)

streamlit_app.py

@@ -0,0 +1,95 @@
+#start
+#to see changes in your local browser just run $ streamlit run streamlit_app.py
+import streamlit as st
+from streamlit_webrtc import webrtc_streamer, WebRtcMode, ClientSettings
+import sounddevice as sd
+import server
+from st_audiorec import st_audiorec
+import nemo.collections.asr as nemo_asr
+from pydub import AudioSegment
+import io
+import os
+import uuid 
+
+global language
+
+
+st.title("Customer Care")
+
+
+@st.cache_resource
+def get_model():
+    try:
+        os.makedirs("audio_cache")
+    except: 
+        pass
+    en_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from("en_am_model/Conformer-CTC-BPE-Large.nemo")
+
+    return en_asr_model
+
+en_asr_model = get_model()
+
+st.title("💬 Vocalize: Empower Your Voice ")
+language = st.selectbox(
+    'Enter your preferred language',
+    ('en', 'hi'))
+
+
+"""
+Hi cord the audio, and get the transcription in real time!
+Note: Works best for smaller audios"""
+
+
+global client_id
+
+client_id=None
+
+language = st.selectbox(
+    'Enter your preferred language',
+    ('en', 'hi'))
+
+
+
+if language==None:
+    st.error("Please enter a valid language.")
+
+wav_audio_data = st_audiorec()
+if wav_audio_data:
+    audio_location = "audio_cache/" + str(uuid.uuid4()) + ".wav"
+    audio_file = io.BytesIO(wav_audio_data)
+    audio = AudioSegment.from_file(audio_file)
+    audio = audio.set_sample_width(2)
+    audio = audio.set_channels(1)
+    audio = audio.set_frame_rate(16000)
+    audio.export(audio_location, format="wav")
+
+    text = en_asr_model.transcribe([audio_location], logprobs=False)[0]
+    print(text)
+    st.write(text)
+
+st.header("Want to transcribe files larger than 2 minutes?")
+uploaded_file=st.file_uploader("upload your recording ",  disabled=False, label_visibility="visible")
+if uploaded_file is not None:
+    # Store the uploaded file:
+    with open(uploaded_file.name, "wb") as f:
+        f.write(uploaded_file.getbuffer())
+    isTranslate=st.button("Click me for translation")
+    # Trigger transcription:
+    if isTranslate and language!=None:                
+        client_id= server.asr(uploaded_file.name,language)
+        st.write("your id for recieving the transcribed File",client_id)
+
+
+st.header('Results')
+
+client_id = st.text_input("Enter your id")
+clicked=st.button("Click me for  transcribed File")
+if clicked:
+    resp=server.get_transcription(str(client_id),language)
+    print(resp,"this is the requested file path")
+    with open(resp, "rb") as file:  
+        st.download_button(
+            "Download transcription",
+            file,  
+            file_name="transcription.txt"  
+            )

streamlit_audio_recorder_app.py

@@ -0,0 +1,44 @@
+# pip install streamlit
+# pip install audio-recorder-streamlit
+
+import streamlit as st
+from st_audiorec import st_audiorec
+import nemo.collections.asr as nemo_asr
+from pydub import AudioSegment
+import io
+import os
+import uuid 
+
+@st.cache_resource
+def get_model():
+    try:
+        os.makedirs("audio_cache")
+    except: 
+        pass
+    en_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from("/home/akshat/v1/en_am_model/Conformer-CTC-BPE-Large.nemo")
+
+    return en_asr_model
+
+en_asr_model = get_model()
+
+st.title("💬 Vocalize: Empower Your Voice ")
+
+"""
+Hi record the audio, and get the transcription in real time!
+Note: Works best for smaller audios
+"""
+
+wav_audio_data = st_audiorec()
+
+if wav_audio_data:
+    audio_location = "audio_cache/" + str(uuid.uuid4()) + ".wav"
+    audio_file = io.BytesIO(wav_audio_data)
+    audio = AudioSegment.from_file(audio_file)
+    audio = audio.set_sample_width(2)
+    audio = audio.set_channels(1)
+    audio = audio.set_frame_rate(16000)
+    audio.export(audio_location, format="wav")
+
+    text = en_asr_model.transcribe([audio_location], logprobs=False)[0]
+    print(text)
+    st.write(text)