Upload 8 files

app.py

@@ -0,0 +1,45 @@
+import streamlit as st
+import youtubetranscript
+import youtubevideo
+import transcriptFromWhisper
+import sourcetoTarget
+import textToSpeech
+from pytube import YouTube
+
+link = st.text_input("Youtube Link")
+st.selectbox("Target Language", ["German"])
+btnTranslate = st.button("Translate video")
+
+
+if btnTranslate:
+    video = YouTube(link)
+    videoId = video.video_id
+    wasSuccessful = youtubetranscript.getTranscript(videoId)
+    if(wasSuccessful):
+        fname = video.video_id + ".mp4"
+        youtubevideo.Download(video, fname)
+    
+    st.video(f"videos\{videoId}.mp4")
+    cols = st.columns(3)
+    cols[0].header(f'Original')
+    cols[1].header(f'Whisper')
+    cols[2].header(f'German')
+    file_path = f"transcripts/{videoId}.txt"
+    with open(file_path, 'r', encoding='utf8') as f: 
+        cols[0].write(f.read())
+
+    transcriptFromWhisper.getWhisperTranscript(videoId)
+    file_path = f"whisper/{videoId}.txt"
+    with open(file_path, 'r') as f: 
+        text = f.read()
+        text = text.replace("$","dollar")
+        print(text)
+        cols[1].write(text)
+
+    sourcetoTarget.englishToGerman(videoId)
+    file_path = f"translatedTranscripts/{videoId}.txt"
+    with open(file_path, 'r', encoding='utf8') as f: 
+        cols[2].write(f.read())
+    
+    textToSpeech.ttsSingleFile(videoId)
+    st.audio(f"tts\{videoId}.wav")

requirements.txt

@@ -0,0 +1,165 @@
+absl-py==2.0.0
+aiohttp==3.9.1
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyascii==0.3.2
+attrs==23.1.0
+audioread==3.0.1
+Babel==2.13.1
+bangla==0.0.2
+blinker==1.7.0
+blis==0.7.11
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.6
+cachetools==5.3.2
+catalogue==2.0.10
+certifi==2023.11.17
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.16.0
+colorama==0.4.6
+confection==0.1.4
+contourpy==1.2.0
+coqpit==0.0.17
+cycler==0.12.1
+cymem==2.0.8
+Cython==3.0.6
+dateparser==1.1.8
+decorator==5.1.1
+docopt==0.6.2
+einops==0.7.0
+encodec==0.1.1
+filelock==3.13.1
+Flask==3.0.0
+fonttools==4.45.1
+frozenlist==1.4.0
+fsspec==2023.10.0
+g2pkk==0.1.2
+gitdb==4.0.11
+GitPython==3.1.40
+google-auth==2.24.0
+google-auth-oauthlib==1.1.0
+grpcio==1.59.3
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut-lang-de==2.0.0
+gruut-lang-en==2.0.0
+gruut-lang-es==2.0.0
+gruut-lang-fr==2.0.2
+hangul-romanize==0.1.0
+huggingface-hub==0.19.4
+idna==3.6
+importlib-metadata==6.8.0
+inflect==7.0.0
+itsdangerous==2.1.2
+jamo==0.4.1
+jieba==0.42.1
+Jinja2==3.1.2
+joblib==1.3.2
+jsonlines==1.2.0
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kiwisolver==1.4.5
+langcodes==3.3.0
+lazy_loader==0.3
+librosa==0.10.1
+llvmlite==0.41.1
+Markdown==3.5.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+more-itertools==10.1.0
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+murmurhash==1.0.10
+networkx==2.8.8
+nltk==3.8.1
+num2words==0.5.13
+numba==0.58.1
+numpy==1.26.2
+oauthlib==3.2.2
+openai-whisper @ git+https://github.com/openai/whisper.git@e58f28804528831904c3b6f2c0e473f346223433
+packaging==23.2
+pandas==1.5.3
+Pillow==10.1.0
+platformdirs==4.0.0
+pooch==1.8.0
+preshed==3.0.9
+protobuf==4.23.4
+psutil==5.9.6
+pyarrow==14.0.1
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pycparser==2.21
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydeck==0.8.1b0
+Pygments==2.17.2
+pynndescent==0.5.11
+pyparsing==3.1.1
+pypinyin==0.49.0
+pysbd==0.3.4
+python-crfsuite==0.9.9
+python-dateutil==2.8.2
+pytube==15.0.0
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.31.1
+regex==2023.10.3
+requests==2.31.0
+requests-oauthlib==1.3.1
+rich==13.7.0
+rpds-py==0.13.2
+rsa==4.9
+safetensors==0.4.1
+scikit-learn==1.3.2
+scipy==1.11.4
+six==1.16.0
+smart-open==6.4.0
+smmap==5.0.1
+soundfile==0.12.1
+soxr==0.3.7
+spacy==3.7.2
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+streamlit==1.29.0
+SudachiDict-core==20230927
+SudachiPy==0.6.7
+sympy==1.12
+tenacity==8.2.3
+tensorboard==2.15.1
+tensorboard-data-server==0.7.2
+thinc==8.2.1
+threadpoolctl==3.2.0
+tiktoken==0.5.1
+tokenizers==0.15.0
+toml==0.10.2
+toolz==0.12.0
+torch==2.1.1
+torchaudio==2.1.1
+tornado==6.4
+tqdm==4.66.1
+trainer==0.0.32
+transformers==4.35.2
+TTS==0.21.2
+typer==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+tzlocal==5.2
+umap-learn==0.5.5
+Unidecode==1.3.7
+urllib3==2.1.0
+validators==0.22.0
+wasabi==1.1.2
+watchdog==3.0.0
+weasel==0.3.4
+Werkzeug==3.0.1
+whisper==1.1.10
+yarl==1.9.3
+youtube-transcript-api==0.6.1
+zipp==3.17.0

sourcetoTarget.py

@@ -0,0 +1,70 @@
+# Transformers installation
+# pip install transformers
+
+import os
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+
+# define tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
+model = AutoModelForSeq2SeqLM.from_pretrained(
+        "facebook/nllb-200-distilled-600M")
+
+
+# translation function for single sentence
+def translateSentence(sentence):
+    inputs = tokenizer(sentence, return_tensors="pt")
+    translated_tokens = model.generate(
+        **inputs, forced_bos_token_id=tokenizer.lang_code_to_id["deu_Latn"], max_length=400
+    )
+    translatedSentence = tokenizer.batch_decode(
+        translated_tokens, skip_special_tokens=True)[0]
+    return translatedSentence
+
+def translateAllTranscripts():
+
+    # source text directory
+    directory = os.fsencode("whisper")
+
+    # go through source text files
+    # translate them to target language (German)
+    #  save translated text files to translatedTranscripts file
+    for file in os.listdir(directory):
+        filename = os.fsdecode(file)
+        print(f'reading {filename}')
+        if (filename.endswith(".txt")):
+            file_path = f"whisper/{filename}"
+            with open(file_path, 'r') as f:
+                sourceText = f.read()  # read source text
+                sentences = sourceText.split('.')
+                translationArr = []
+                for sentence in sentences:
+                    #  translate each sentence
+                    translatedSentence = translateSentence(sentence)
+                    translationArr.append(translatedSentence)
+                # join translated sentences
+                translation = " ".join(translationArr)
+                # save translated transcript
+                fname = "translatedTranscripts/" + filename
+                with open(fname, "w", encoding="UTF8") as ft:
+                    ft.write(translation)
+                    print("written to: " + fname)
+
+
+def englishToGerman(videoId):
+    file_path = f"whisper/{videoId}.txt"
+    with open(file_path, 'r') as f:
+        sourceText = f.read()  # read source text
+        sentences = sourceText.split('.')
+        translationArr = []
+        for sentence in sentences:
+            #  translate each sentence
+            translatedSentence = translateSentence(sentence)
+            translationArr.append(translatedSentence)
+        # join translated sentences
+        translation = " ".join(translationArr)
+        # save translated transcript
+        fname = f"translatedTranscripts/{videoId}.txt" 
+        with open(fname, "w", encoding="UTF8") as ft:
+            ft.write(translation)
+            print("written to: " + fname)

textToSpeech.py

@@ -0,0 +1,33 @@
+# !pip install tts
+# !pip install python-espeak-ng
+
+from TTS.api import TTS
+import os
+
+# Init TTS with the target model name
+tts = TTS(model_name="tts_models/de/thorsten/tacotron2-DDC", progress_bar=False)
+
+
+def ttsForAllFiles():
+    # source text directory
+    directory = os.fsencode("translatedTranscripts")
+
+    # go through source text files
+    for file in os.listdir(directory):
+        filename = os.fsdecode(file)
+        print(f'reading {filename}')
+        if (filename.endswith(".txt")):
+            file_path = f"translatedTranscripts/{filename}"
+            with open(file_path, 'r', encoding='utf8') as f:
+                sourceText = f.read()  # read source text
+                fname = filename.replace(".txt", "")
+                # Run TTS
+                tts.tts_to_file(text=sourceText, file_path=f"tts/{fname}.wav")
+
+
+def ttsSingleFile(videoId):
+    file_path = f"translatedTranscripts/{videoId}.txt"
+    with open(file_path, 'r', encoding='utf8') as f:
+        sourceText = f.read()  # read source text
+        # Run TTS
+        tts.tts_to_file(text=sourceText, file_path=f"tts/{videoId}.wav")

transcriptFromWhisper.py

@@ -0,0 +1,25 @@
+import whisper
+import os
+
+def getAllWhisperTranscripts():
+    directory = os.fsencode("videos")
+
+    for file in os.listdir(directory):
+        filename = os.fsdecode(file)
+        print(filename)
+
+        model = whisper.load_model("tiny")
+        result = model.transcribe("videos/" + filename, fp16=False)
+        fname = "whisper/" + filename
+        fname = fname.replace(".mp4", ".txt") 
+        with open(fname, "w") as f:
+            f.write(result["text"])
+            print("written to: " + fname)
+
+def getWhisperTranscript(videoId):
+    model = whisper.load_model("tiny")
+    result = model.transcribe(f"videos/{videoId}.mp4", fp16=False)
+    fname = f"whisper/{videoId}.txt"
+    with open(fname, "w") as f:
+        f.write(result["text"])
+        print("written to: " + fname)

videosFromPlaylist.py

@@ -0,0 +1,22 @@
+import youtubetranscript
+import youtubevideo
+from pytube import Playlist
+
+playlist = Playlist('https://www.youtube.com/playlist?list=PLI1yx5Z0Lrv77D_g1tvF9u3FVqnrNbCRL')
+print('Number of videos in playlist: %s' % len(playlist.video_urls))
+videoCount = 10
+
+i = 1
+
+for video in playlist.videos:
+    print(f'VIDEO {i}:')
+    print(video.title + ": " + video.video_id)
+    wasSuccessful = youtubetranscript.getTranscript(video.video_id)
+    if(wasSuccessful):
+        fname = video.video_id + ".mp4"
+        youtubevideo.Download(video, fname)
+        i = i + 1
+    if(i > videoCount):
+        break
+
+

youtubetranscript.py

@@ -0,0 +1,16 @@
+from youtube_transcript_api import YouTubeTranscriptApi 
+
+def getTranscript(videoId):
+    try:        
+        srt =  YouTubeTranscriptApi.get_transcript(videoId)
+        fname = "transcripts/" + videoId + ".txt"
+        with open(fname, "w") as f:
+            # iterating through each element of list srt
+            for i in srt:
+                # writing each element of srt on a new line
+                f.write("{}\n".format(i["text"]).replace("\xa0", " ").replace(" — ", " "))
+        return True
+    except:
+        print("A transcript error has occurred")
+        return False
+    

youtubevideo.py

@@ -0,0 +1,13 @@
+from pytube import YouTube
+
+SAVE_DIRECTORY = "./videos"
+
+def Download(video, fname):
+    video = video.streams.get_highest_resolution()
+    try:        
+        video.download(SAVE_DIRECTORY, filename=fname)
+        print("Download is completed successfully")
+    except:
+        print("A video error has occurred")
+
+