app.py

from google.colab import files
uploaded = files.upload()
path = next(iter(uploaded))

num_speakers = 2 #@param {type:"integer"}

language = 'English' #@param ['any', 'English']

model_size = 'large' #@param ['tiny', 'base', 'small', 'medium', 'large']


model_name = model_size
if language == 'English' and model_size != 'tiny':
  model_name += '.en'

!pip install -q git+https://github.com/openai/whisper.git > /dev/null
!pip install -q git+https://github.com/pyannote/pyannote-audio > /dev/null

import whisper
import datetime

import subprocess

import torch
import pyannote.audio
from pyannote.audio.pipelines.speaker_verification import PretrainedSpeakerEmbedding
embedding_model = PretrainedSpeakerEmbedding(
    "speechbrain/spkrec-ecapa-voxceleb",
    device=torch.device("cuda"))

from pyannote.audio import Audio
from pyannote.core import Segment

import wave
import contextlib

from sklearn.cluster import AgglomerativeClustering
import numpy as np


if path[-3:] != 'wav':
  subprocess.call(['ffmpeg', '-i', path, 'audio.wav', '-y'])
  path = 'audio.wav'

model = whisper.load_model(model_size)

result = model.transcribe(path)
segments = result["segments"]

with contextlib.closing(wave.open(path,'r')) as f:
  frames = f.getnframes()
  rate = f.getframerate()
  duration = frames / float(rate)

audio = Audio()

def segment_embedding(segment):
  start = segment["start"]
 
  end = min(duration, segment["end"])
  clip = Segment(start, end)
  waveform, sample_rate = audio.crop(path, clip)
  return embedding_model(waveform[None])

embeddings = np.zeros(shape=(len(segments), 192))
for i, segment in enumerate(segments):
  embeddings[i] = segment_embedding(segment)

embeddings = np.nan_to_num(embeddings)

clustering = AgglomerativeClustering(num_speakers).fit(embeddings)
labels = clustering.labels_
for i in range(len(segments)):
  segments[i]["speaker"] = 'SPEAKER ' + str(labels[i] + 1)
  # speaker = 'Held'
  # speaker = 'Heldisha'
  # if segments[i]["speaker"]== 'SPEAKER 1':
  #   segments[i]["speaker"] = 'Held'
  # elif segments[i]["speaker"]== 'SPEAKER 2':
  #   segments[i]["speaker"] = 'Heldisha'
  # if segments[i]["speaker"]== 'SPEAKER 1':
    # segments[i]["speaker"] = segments.index('n')
# k = list(segments)
# print(k[5])

def time(secs):
  return datetime.timedelta(seconds=round(secs))

f = open("transcript.txt", "w")

for (i, segment) in enumerate(segments):
  if i == 0 or segments[i - 1]["speaker"] != segment["speaker"]:
    f.write("\n" + segment["speaker"] + ' ' + str(time(segment["start"])) + '\n')
  f.write(segment["text"][1:] + ' ')
f.close()

# with open('transcript.txt', 'r') as file:
#     text = file.read()
#     words = text.split()
#     i = words.index('name')
#     if (words[i-1] == 'My') or (words[i-1] == 'my') and (words[i+1] == 'is'):
#         name1 = words[i+2]
#         print(name1)
  
#     with open('transcript.txt', 'r') as file:
#         text = file.read()
#         new_text = text.replace('SPEAKER 1', name1)
#     with open('transcript.txt', 'w') as file:
#         file.write(new_text)



# with open('transcript.txt', 'r') as file:
    
#     text = file.read()
#     words = text.split()
#     i = words.index('name')
#     if (words[i+3] == 'What') or (1<2) and (words[i+1] == 'is') or 1<2:
#         name2 = words[i+22]
#         print(name2)
#     with open('transcript.txt', 'r') as file:
#         text = file.read()
#         new_text = text.replace('SPEAKER 2', name2)
#     with open('transcript.txt', 'w') as file:
#         file.write(new_text)