port

.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/.idea/*
+/.venv/*
+/__pycache__/*
+/.segments/*
+../.segments/*
+../.segments/
+../__pycache__/

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,12 +1,12 @@
 ---
-title: Streamlit Template Space
+title: AICallCenter2
 emoji: 🚀
 colorFrom: red
 colorTo: red
 sdk: docker
 app_port: 8501
 tags:
-  - streamlit
+- streamlit
 pinned: false
 short_description: Streamlit template space
 ---

make_env

@@ -0,0 +1,12 @@
+pip uninstall torch torchvision torchaudio
+
+pip install torch==2.7.0 --index-url https://download.pytorch.org/whl/cu126
+pip install torchaudio==2.7.0 --index-url https://download.pytorch.org/whl/cu126
+pip install torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu126
+
+pip install -r requirements.txt
+
+git config --global user.email "jerryf31415@gmail.com"
+git config --global user.name "jerry flynn"
+
+streamlit run ./src/app.py 

requirements.txt

@@ -1,3 +1,165 @@
-altair
-pandas
-streamlit
+accelerate==1.6.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.17
+aiosignal==1.3.2
+alembic==1.15.2
+altair==5.5.0
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.9.0
+assemblyai==0.38.0
+asteroid-filterbanks==0.4.0
+async-timeout==5.0.1
+attrs==25.3.0
+bibtexparser==1.4.3
+binaryornot==0.4.4
+blinker==1.9.0
+bracex==2.5.post1
+cachetools==5.5.2
+certifi==2025.1.31
+cffi==1.17.1
+chardet==5.2.0
+charset-normalizer==3.4.1
+click==8.1.8
+colorama==0.4.6
+colorlog==6.9.0
+contourpy==1.3.2
+cycler==0.12.1
+distro==1.9.0
+dnspython==2.7.0
+docopt==0.6.2
+einops==0.8.1
+email_validator==2.2.0
+exceptiongroup==1.2.2
+filelock==3.18.0
+filetype==1.2.0
+fonttools==4.57.0
+frozenlist==1.6.0
+fsspec==2025.3.2
+gitdb==4.0.12
+GitPython==3.1.44
+greenlet==3.2.0
+h11==0.14.0
+httpcore==1.0.8
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.30.2
+HyperPyYAML==1.2.2
+idna==3.10
+insanely-fast-whisper==0.0.15
+Jinja2==3.1.6
+jiter==0.9.0
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2025.4.1
+julius==0.2.7
+kiwisolver==1.4.8
+lightning==2.5.1
+lightning-utilities==0.14.3
+llvmlite==0.44.0
+Mako==1.3.10
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.10.1
+mdurl==0.1.2
+monty==2025.3.3
+more-itertools==10.6.0
+mpmath==1.3.0
+mrcfile==1.5.4
+multidict==6.4.3
+narwhals==1.37.0
+networkx==3.4.2
+numba==0.61.2
+numpy==2.2.5
+omegaconf==2.3.0
+openai==1.76.0
+openai-whisper==20240930
+optimum==1.24.0
+optuna==4.3.0
+orjson==3.10.16
+packaging==24.2
+palettable==3.3.3
+pandas==2.2.3
+pillow==11.2.1
+plotly==6.0.1
+primePy==1.3
+propcache==0.3.1
+protobuf==5.29.4
+psutil==7.0.0
+pyannote.audio==3.3.2
+pyannote.core==5.0.0
+pyannote.database==5.1.3
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pyarrow==20.0.0
+pycparser==2.22
+pydantic==2.11.3
+pydantic_core==2.33.1
+pydeck==0.9.1
+pydub==0.25.1
+Pygments==2.19.1
+pymatgen==2025.4.24
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytorch-lightning==2.5.1
+pytorch-metric-learning==2.8.1
+pytz==2025.2
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+rich==14.0.0
+rich-toolkit==0.14.3
+rpds-py==0.24.0
+ruamel.yaml==0.18.10
+ruamel.yaml.clib==0.2.12
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.2
+semver==3.0.4
+sentencepiece==0.2.0
+shellingham==1.5.4
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+sortedcontainers==2.4.0
+soundfile==0.13.1
+speechbrain==1.0.3
+spglib==2.6.0
+SQLAlchemy==2.0.40
+starlette==0.37.2
+streamlit==1.44.1
+streamlit-ace==0.1.1
+streamlit-antd==0.8.3
+streamlit-embeded==0.0.1
+streamlit-molstar==0.4.21
+sympy==1.13.1
+tabulate==0.9.0
+tenacity==9.1.2
+tensorboardX==2.6.2.2
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.21.1
+toml==0.10.2
+torch-audiomentations==0.12.0
+torch_pitch_shift==1.2.5
+torchao
+torchmetrics==1.7.1
+tornado==6.4.2
+tqdm==4.67.1
+transformers==4.51.3
+typer==0.15.2
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+tzdata==2025.2
+ujson==5.10.0
+uncertainties==3.2.3
+urllib3==2.4.0
+uvicorn==0.34.2
+watchdog==6.0.0
+watchfiles==1.0.5
+wcmatch==10.0
+websockets==15.0.1
+yarl==1.20.0

src/CallCenter.py

@@ -0,0 +1,98 @@
+# Install the assemblyai package by executing the command `pip3 install assemblyai` (macOS) or `pip install assemblyai` (Windows).
+import io
+import os
+import time
+from pyannote.audio import Pipeline
+
+# Import the AssemblyAI module
+from pprint import pprint
+import torch
+from transformers import pipeline
+from transformers.utils import is_flash_attn_2_available
+from pydub import AudioSegment
+import numpy as np
+
+from segment_wave_files import segment_wave_files
+from transcribe_files import transcribe_segments
+from transcript_analysis import transcript_analysis
+#from huggingface_hub import login
+#login()
+hugging_face = os.environ.get("HUGGING_FACE")
+pipelineDiary = Pipeline.from_pretrained(
+    "pyannote/speaker-diarization-3.1",
+    use_auth_token=hugging_face)
+
+pipelineDiary.to(torch.device("cuda"))
+
+def diarize_wav_file(file_name):
+    print("DIARIZING " + file_name)
+    start = time.time()
+    diarization = pipelineDiary(file_name, num_speakers=2)
+    print("Elapsed " + str(time.time() - start))
+    # {"waveform": audio_tensor, "sample_rate": sample_rate_tensor})
+    speakers = []
+    contSpeaker = ""
+    dict = None
+    for turn, _, speaker in diarization.itertracks(yield_label=True):
+        if contSpeaker != speaker:
+            if dict is not None:
+                speakers.append(dict)
+            dict = {'speaker': speaker, 'start': round(turn.start, 1),
+                    'end': round(turn.end, 1)}
+            contSpeaker = speaker
+        else:
+            dict['end'] = round(turn.end, 1)
+
+    return speakers
+
+
+def convert_mono_16khz(location, file):
+    sound = AudioSegment.from_file(location+file, "wav")
+    sound = sound.set_channels(1)
+    sound = sound.set_frame_rate(16000)
+    sound.export(location+"16khz"+file, "wav")
+
+location = os.path.join(".", "data") + os.sep
+def get_included_files():
+    files = os.listdir(location)
+
+    return location, files
+
+def main():
+
+    dir_list = os.listdir(location)
+    for file in dir_list :
+        #input_file=location+file
+        input_file='C:\\Users\\jerry\\Downloads\\SampleCallsWave\\Tech Support Help from Call Center Experts1.wav'
+
+        # apply pretrained pipeline
+        # Pass the audio tensor and sample rate to the pipeline
+        speakers = diarize_wav_file(input_file)
+
+        speakers = segment_wave_files(speakers, input_file)
+
+        transcript = transcribe_segments(speakers)
+        print(
+            "---------------------------------------------------------------------")
+        pprint(transcript)
+        print("---------------------------------------------------------------------")
+
+        summary = transcript_analysis(transcript)
+        pprint(summary) #.encode('utf-8').decode('utf-8'))
+        print("\n\n\n\n\n\n\n")
+
+def convertMp3ToWav(file) :
+    # convert mp3 file to a wav file
+    sound = AudioSegment.from_mp3(file)
+    # sound.export(output_file, format="wav")
+
+    sample_rate = sound.frame_count() / sound.duration_seconds
+    print(sample_rate)
+    duration = sound.duration_seconds
+    sound = sound.set_frame_rate(16000)
+    sound = sound.set_channels(1)
+    outFile = os.path.splitext(file)[0]+".wav"
+    sound.export(outFile, format="wav")
+    return outFile
+
+main()

src/app.py

@@ -0,0 +1,88 @@
+import streamlit as st
+import pandas as pd
+from CallCenter import get_included_files, convertMp3ToWav, diarize_wav_file
+import os
+
+from segment_wave_files import segment_wave_files
+from transcript_analysis import transcript_analysis
+from transcribe_files import transcribe_segments
+
+location, wave_files = get_included_files()
+
+
+def main():
+    # --- Streamlit App ---
+    st.title("Call Center Analysis")
+
+    # --- Selectable Elements ---
+
+    def get_file_sel():
+        if selected_file is None:
+            return
+        st.session_state.selected_file = location+selected_file  # Store the selected option in session state
+        st.write(f"{selected_file} is selected") # Display feedback
+        st.session_state.wave_file = st.session_state.selected_file
+
+    selected_file = st.selectbox("Select an element:", wave_files)
+    get_file_sel()
+
+    # --- File Upload ---
+    uploaded_file = st.file_uploader("Upload a file", type=['mp3', 'wav'])
+    if uploaded_file:
+        st.session_state.uploaded_file = uploaded_file.name
+        if st.session_state.uploaded_file is not None:
+            if os.path.splitext(uploaded_file.name)[1].lower()==".mp3":
+                bytes_data = uploaded_file.read()  # read the content of the file in binary
+                if not os.path.exists("/tmp"):
+                    os.makedirs("/tmp")
+
+                with open(os.path.join("/tmp", uploaded_file.name), "wb") as f:
+                    f.write(bytes_data)  # write this content elsewhere
+                wav_file = convertMp3ToWav(f"/tmp/{uploaded_file.name}")
+                st.session_state.wave_file = wav_file  # Store the selected option in session state
+            else:
+                bytes_data = uploaded_file.read()  # read the content of the file in binary
+                with open(os.path.join("/tmp", uploaded_file.name), "wb") as f:
+                    f.write(bytes_data)  # write this content elsewhere
+                st.session_state.wave_file = os.path.join("/tmp", uploaded_file.name)  # Store the selected option in session state
+
+            st.write(f"You uploaded: {uploaded_file.name}")  # Display feedback
+        uploaded_file = None
+
+    analysis = ""
+    # --- Start Button ---
+    if st.button("Start"):
+        if st.session_state.wave_file is not None:
+            with st.spinner("Please wait..."):
+                try:
+                    speakers = diarize_wav_file(st.session_state.wave_file )
+
+                    speakers = segment_wave_files(speakers, st.session_state.wave_file )
+
+                    transcripts = transcribe_segments(speakers)
+                    analysis = transcript_analysis(transcripts)
+                except Exception as e:
+                    st.error(f"Error processing file: {st.session_state.wave_file}")
+        else:
+            st.warning("Please upload a file.")
+
+    # --- Reset Button ---
+    if st.button("Reset"):
+        st.experimental_rerun()
+
+    # --- Large Text Box (Display Only) ---
+    if analysis != "":
+        analysis = analysis[9:]
+        index=analysis.lower().find("sentiment")
+        summary=analysis[0:index].lstrip("\n")
+
+        sentiment = analysis[index:]
+        index=sentiment.lower().find(":")
+        sentiment = sentiment[index+1:].lstrip("\n")
+
+        height = 34*15
+        st.text_area("SUMMARY:", value=summary, disabled=True, height=height)
+        st.text_area("SENTIMENT:", value=sentiment, disabled=True, height=height)
+
+
+main()

src/segment_wave_files.py

@@ -0,0 +1,31 @@
+import os
+from pydub import AudioSegment
+import shutil
+
+
+def segment_wave_files(speakers, file):
+
+    folder = ".segments"
+    if os.path.exists(folder):
+        shutil.rmtree(folder)
+    if not os.path.exists(folder):
+        os.makedirs(folder)
+
+    audio = AudioSegment.from_file(file, format="wav")#.resample(sample_rate_Hz=8000, sample_width=2, channels=1)
+
+    i=0
+    speakers_out = []
+    for speaker in speakers:
+        # {'speaker': speaker, 'start': round(turn.start, 1), 'end': round(turn.end, 1)}
+        start = speaker['start']*1000
+        stop = speaker['end']*1000
+        clip = audio[start:stop]
+        clip_name = folder+"\\clipFor"+speaker['speaker']+"_"+str(i)+".wav"
+        i+=1
+        clip.export(clip_name, format="wav")
+        speaker['clipFile'] = clip_name
+        speakers_out.append(speaker)
+
+    return speakers_out
+
+

src/transcribe_files.py

@@ -0,0 +1,36 @@
+import os
+
+import whisper
+import time
+def transcribe_segments(speakers):
+    print(f"Whisper models {whisper.available_models()}")
+    model = whisper.load_model("tiny.en", device="cuda")
+    #model = whisper.load_model("medium.en", device="cuda")
+#    model = whisper.load_model("turbo", device="cuda")
+    #model = whisper.load_model("large-v3-turbo", device="cuda")
+    transcripts = []
+    input_file = ""
+    print("Transcribing ALL segments")
+    total_start = time.time()
+    for speaker in speakers:
+        # {'speaker': speaker, 'start': round(turn.start, 1),
+        #  'end': round(turn.end, 1), 'clipFile':clipName}
+        input_file = speaker['clipFile']
+
+        print("TRANSCRIBING " + input_file)
+        start = time.time()
+        transcript = model.transcribe(input_file)
+        print("Elapsed " + str(time.time() - start))
+        segments = transcript["segments"]
+        outText = ""
+        for segment in segments:
+            outText += segment['text']
+
+        transcripts.append(speaker['speaker']+" : "+outText)
+        os.remove(input_file)
+
+    print("Total Elapsed " + str(time.time() - total_start))
+    currdir= input_file[0:input_file.index('\\')]
+    os.rmdir(currdir)
+
+    return transcripts

src/transcript_analysis.py

@@ -0,0 +1,131 @@
+from encodings.utf_8 import encode
+
+from openai import OpenAI
+import time
+from transformers import pipeline
+
+def use_openai(input):
+    client = OpenAI()
+    response = client.responses.create(
+        model="o3-mini-2025-01-31",
+        # model="gpt-4.1",
+        input=f"""You are an helpful assistant.  Analyze the following transcript and 
+        give a summary of the conversation.  Also give the sentiment of each speaker 
+        as the conversation progresses. Also replace Speaker_0x with name or title 
+        if it can be derived from conversation. Response should only contain ascii 
+        characters. {input}"""
+    )
+    return response.output_text
+
+from transformers import BigBirdPegasusForConditionalGeneration, AutoTokenizer
+def use_bigbird_pegasus_large_arxiv(input):
+
+    tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")
+
+    # by default encoder-attention is `block_sparse` with num_random_blocks=3, block_size=64
+    model = BigBirdPegasusForConditionalGeneration.from_pretrained("google/bigbird-pegasus-large-arxiv")
+
+    # decoder attention type can't be changed & will be "original_full"
+    # you can change `attention_type` (encoder only) to full attention like this:
+    model = BigBirdPegasusForConditionalGeneration.from_pretrained("google/bigbird-pegasus-large-arxiv", attention_type="original_full")
+
+    # you can change `block_size` & `num_random_blocks` like this:
+    model = BigBirdPegasusForConditionalGeneration.from_pretrained("google/bigbird-pegasus-large-arxiv", block_size=16, num_random_blocks=2)
+
+    input=f"""You are an helpful assistant.  Analyze the following transcript and 
+        give a summary of the conversation.  Also give the sentiment of each speaker 
+        as the conversation progresses. Also replace Speaker_0x with name or title 
+        if it can be derived from conversation. Response should only contain ascii 
+        characters. {input}"""
+    inputs = tokenizer(input, return_tensors='pt')
+    prediction = model.generate(**inputs)
+    prediction = tokenizer.batch_decode(prediction)
+
+import torch
+
+def use_huggingface(input):
+    # Define the model name
+    # model_name = "cnicu/t5-small-booksum"
+    # model_name = "sshleifer/distilbart-cnn-12-6"
+    #model_name = "facebook/bart-large-cnn"
+    model_name = "huggyllama/llama-7b"
+    #model_name = "google/pegasus-large"
+
+#    summarizer = pipeline(task="summarization", model=model_name, device_map="cuda")
+    summarizer = pipeline(task="summarization", model=model_name,
+                          torch_dtype=torch.float16)
+
+
+    max_length = 1024
+    #input = "summarize the following transcript:"+input
+    # length = len(input)
+    # if length < 1024:
+    #     max_length = length
+    # else:
+    #     input = input[0:1023]
+    input = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
+    A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
+    Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other.
+    In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage.
+    Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the
+    2010 marriage license application, according to court documents.
+    Prosecutors said the marriages were part of an immigration scam.
+    On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
+    After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective
+    Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
+    All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say.
+    Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
+    Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
+    The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
+    Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
+    Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
+    If convicted, Barrientos faces up to four years in prison.  Her next court appearance is scheduled for May 18.
+    """
+    # # Pass the long text to the model to summarize it with a maximum length of 50 tokens
+    outputs = summarizer(input, max_length=max_length, do_sample=False)
+    # , min_length = 25, max_length=500
+    # Access and print the summarized text in the outputs variable
+    return outputs[0]['summary_text']
+
+
+from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
+
+def use_huggingface2(input):
+    # Define the model name
+    # model_name = "cnicu/t5-small-booksum"
+    # model_name = "sshleifer/distilbart-cnn-12-6"
+    #model_name = "facebook/bart-large-cnn"
+    model_name = "huggyllama/llama-7b"
+    #model_name = "google/pegasus-large"
+
+    quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name,
+        torch_dtype=torch.bfloat16,
+        device_map="auto",
+        quantization_config=quantization_config
+    )
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    input_ids = tokenizer(input, return_tensors="pt").to("cuda")
+
+    output = model.generate(**input_ids, cache_implementation="static")
+    print(tokenizer.decode(output[0], skip_special_tokens=True))
+
+def transcript_analysis(transcript):
+    results = []
+    #print(os.environ['OPENAI_API_KEY'])
+
+    input=""
+    for speaker in transcript:
+        input += speaker + "\n"
+
+    start = time.time()
+    response = use_huggingface2(input)
+ #   response = use_openai(input)
+    #response = use_bigbird_pegasus_large_arxiv(input)
+    stop = time.time()
+    elapsed=stop-start
+    print("transcript analysis consumed "+str(elapsed))
+
+    return response