push

app.py

@@ -0,0 +1,250 @@
+import numpy as np
+import streamlit as st
+from constants import WHISPER_MODELS, language_dict
+import streamlit as st
+from utils import translate_to_english, detect_language, write, read, get_key
+import whisperx as whisper
+import json
+import pandas as pd
+
+if "btn1" not in st.session_state:
+    st.session_state["btn1"] = False
+if "btn2" not in st.session_state:
+    st.session_state["btn2"] = False
+
+
+class ByteEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, bytes):
+            return obj.hex()
+        return json.JSONEncoder.default(self, obj)
+
+
+def disable_btn2():
+    st.session_state["btn2"] = True
+
+
+def disable_btn1():
+    st.session_state["btn1"] = True
+
+
+st.set_page_config(page_title="Whisper-X", layout="wide")
+import torch
+
+if torch.cuda.is_available():
+    device = "gpu"
+else:
+    device = "cpu"
+input, output = st.columns(2, gap="medium")
+with input:
+    st.header("Input")
+    audio_file = open("audio.wav", "rb")
+    audio_bytes = audio_file.read()
+    # st.markdown("""**sample audio**""", unsafe_allow_html=True)
+    st.audio(audio_bytes, format="audio/wav")
+    # st.markdown("""**your audio file**""", unsafe_allow_html=True)
+    audio_uploaded = st.file_uploader(
+        label="Upload your file",
+        type=["mp3", "wav"],
+        help="Your input file",
+        # on_change=disable_btn2,
+        # disabled=st.session_state["btn1"],
+    )
+    # text_json = st.file_uploader(
+    #     label="Aligned JSON",
+    #     type=["json"],
+    #     help="Your aligned json file",
+    #     # disabled=st.session_state["btn2"],
+    #     # on_change=disable_btn1,
+    # )
+    text_json = None
+
+    # st.markdown("""**model**""", unsafe_allow_html=True)
+    model_name = st.selectbox(
+        label="Choose your model",
+        options=WHISPER_MODELS,
+        help="Choose a Whisper model.",
+    )
+    model_name = "base" if model_name == "" else model_name
+    # st.markdown("**transcription**", unsafe_allow_html=True)
+    transcription = st.selectbox(
+        "transcription",
+        options=["plain text", "srt", "vtt", "ass", "tsv"],
+        help="Choose the format for the transcription",
+    )
+    translate = st.checkbox(
+        "translate", help="Translate the text to English when set to True"
+    )
+    language = st.selectbox(
+        label="language",
+        options=list(language_dict.keys()) + list(language_dict.values()),
+        help="Translate the text to English when set to True",
+    )
+    patience = st.number_input(
+        label="patience",
+        step=0.01,
+        value=1.0,
+        help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search",
+    )
+    temperature = st.number_input(
+        label="temperature",
+        step=0.01,
+        value=1.0,
+        help="temperature to use for sampling",
+    )
+    suppress_tokens = st.text_input(
+        "suppress_tokens",
+        value="-1",
+        help="comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations",
+    )
+    initial_prompt = st.text_area(
+        label="initial_prompt",
+        help="optional text to provide as a prompt for the first window.",
+    )
+    condition_on_previous_text = st.checkbox(
+        "condition_on_previous_text",
+        help="if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop",
+    )
+    temperature_increment_on_fallback = st.number_input(
+        label="temperature_increment_on_fallback",
+        step=0.01,
+        value=0.2,
+        help="temperature to increase when falling back when the decoding fails to meet either of the thresholds below",
+    )
+    compression_ratio_threshold = st.number_input(
+        label="compression_ratio_threshold",
+        value=2.4,
+        step=0.01,
+        help="if the gzip compression ratio is higher than this value, treat the decoding as failed",
+    )
+    logprob_threshold = st.number_input(
+        label="logprob_threshold",
+        value=-1.0,
+        step=0.01,
+        help="if the average log probability is lower than this value, treat the decoding as failed",
+    )
+    no_speech_threshold = st.number_input(
+        label="no_speech_threshold",
+        value=0.6,
+        step=0.01,
+        help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence",
+    )
+    if temperature_increment_on_fallback is not None:
+        temperature = tuple(
+            np.arange(temperature, 1.0 + 1e-6, temperature_increment_on_fallback)
+        )
+    else:
+        temperature = [temperature]
+    # st.write(temperature)
+    submit = st.button("Submit", type="primary")
+with output:
+    st.header("Output")
+    if submit:
+        if audio_uploaded is None:
+            # st.audio(audio_bytes, format="audio/wav")
+            audio_uploaded = audio_file
+        if audio_uploaded is not None:
+
+            # audio_bytes = audio_uploaded.read()
+            # st.audio(audio_bytes, format="audio/wav")
+            if language == "":
+                model = whisper.load_model(model_name)
+                with st.spinner("Detecting language..."):
+                    detection = detect_language(audio_uploaded.name, model)
+                    language = detection.get("detected_language")
+                    del model
+                    # st.write(language)
+            if len(language) > 2:
+                language = get_key(language)
+            segments_pre = st.empty()
+            segments_post = st.empty()
+            segments_post_json = st.empty()
+            segments_post2 = st.empty()
+            trans = st.empty()
+            lang = st.empty()
+            if text_json is None:
+                with st.spinner("Running ... "):
+                    decode = {"suppress_tokens": suppress_tokens, "beam_size": 5}
+                    model = whisper.load_model(model_name)
+                    with st.container():
+                        with st.spinner(f"Running with {model_name} model"):
+                            result = model.transcribe(
+                                audio_uploaded.name,
+                                language=language,
+                                patience=patience,
+                                initial_prompt=initial_prompt,
+                                condition_on_previous_text=condition_on_previous_text,
+                                temperature=temperature,
+                                compression_ratio_threshold=compression_ratio_threshold,
+                                logprob_threshold=logprob_threshold,
+                                no_speech_threshold=no_speech_threshold,
+                                **decode,
+                            )
+
+                if translate:
+                    result = translate_to_english(result, json=False)
+                with open("transcription.json", "w") as f:
+                    json.dump(result["segments"], f, indent=4, cls=ByteEncoder)
+                with st.spinner("Running alignment model ..."):
+                    model_a, metadata = whisper.load_align_model(
+                        language_code=result["language"], device=device
+                    )
+                    result_aligned = whisper.align(
+                        result["segments"],
+                        model_a,
+                        metadata,
+                        audio_uploaded.name,
+                        device=device,
+                    )
+
+            if text_json is not None:
+                if translate:
+                    result = translate_to_english(text_json, json=True)
+                with st.spinner("Running alignment model ..."):
+                    model_a, metadata = whisper.load_align_model(
+                        language_code=language, device=device
+                    )
+
+                    result_aligned = whisper.align(
+                        text_json, model_a, metadata, audio_uploaded.name, device
+                    )
+
+            if text_json is None:
+                words_segments = result_aligned["word_segments"]
+                write(
+                    audio_uploaded.name,
+                    dtype=transcription,
+                    result_aligned=result_aligned,
+                )
+                trans_text = read(audio_uploaded.name, transcription)
+                trans.text_area(
+                    "transcription", trans_text, height=None, max_chars=None, key=None
+                )
+                segments_pre.text_area(
+                    "Segments before alignment",
+                    result["segments"],
+                    height=None,
+                    max_chars=None,
+                    key=None,
+                )
+            segments_post.text_area(
+                "Word Segments after alignment",
+                result_aligned["word_segments"],
+                height=None,
+                max_chars=None,
+                key=None,
+            )
+            with open("segments.json", "w", encoding="utf-8") as f:
+
+                json.dump(result_aligned["word_segments"], f, indent=False)
+
+            segments_post2.text_area(
+                "Segments after alignment",
+                result_aligned["segments"],
+                height=None,
+                max_chars=None,
+                key=None,
+            )
+            lang.text_input(
+                "detected language", language_dict.get(language), disabled=True
+            )

audio.txt

@@ -0,0 +1,9 @@
+Right now, at this very second, we're in the aftermath of the Big Bang
+Everything we see.
+And here, and police...
+and smell.
+And touch, is the aftermath
+The Big Bang is really our evolving, expanding universe
+For us, mostly stuck on our rocky little planet
+the view of the universe begins with earth
+This is Earth

constants.py

@@ -0,0 +1,183 @@
+LANGUAGES = [
+    "English",
+    "Chinese",
+    "German",
+    "Spanish",
+    "Russian",
+    "Korean",
+    "French",
+    "Japanese",
+    "Portuguese",
+    "Turkish",
+    "Polish",
+    "Catalan",
+    "Dutch",
+    "Arabic",
+    "Swedish",
+    "Italian",
+    "Indonesian",
+    "Hindi",
+    "Finnish",
+    "Vietnamese",
+    "Hebrew",
+    "Ukrainian",
+    "Greek",
+    "Malay",
+    "Czech",
+    "Romanian",
+    "Danish",
+    "Hungarian",
+    "Tamil",
+    "Norwegian",
+    "Thai",
+    "Urdu",
+    "Croatian",
+    "Bulgarian",
+    "Lithuanian",
+    "Latin",
+    "Maori",
+    "Malayalam",
+    "Welsh",
+    "Slovak",
+    "Telugu",
+    "Persian",
+    "Latvian",
+    "Bengali",
+    "Serbian",
+    "Azerbaijani",
+    "Slovenian",
+    "Kannada",
+    "Estonian",
+    "Macedonian",
+    "Breton",
+    "Basque",
+    "Icelandic",
+    "Armenian",
+    "Nepali",
+    "Mongolian",
+    "Bosnian",
+    "Kazakh",
+    "Albanian",
+    "Swahili",
+    "Galician",
+    "Marathi",
+    "Punjabi",
+    "Sinhala",
+    "Khmer",
+    "Shona",
+    "Yoruba",
+    "Somali",
+    "Afrikaans",
+    "Occitan",
+    "Georgian",
+    "Belarusian",
+    "Tajik",
+    "Sindhi",
+    "Gujarati",
+    "Amharic",
+    "Yiddish",
+    "Lao",
+    "Uzbek",
+    "Faroese",
+    "Haitian Creole",
+    "Pashto",
+    "Turkmen",
+    "Nynorsk",
+    "Maltese",
+    "Sanskrit",
+    "Luxembourgish",
+    "Myanmar",
+    "Tibetan",
+    "Tagalog",
+    "Malagasy",
+    "Assamese",
+    "Tatar",
+    "Hawaiian",
+    "Lingala",
+    "Hausa",
+    "Bashkir",
+    "Javanese",
+    "Sundanese",
+]
+
+WHISPER_MODELS = [
+    "",
+    "tiny",
+    "base",
+    "small",
+    "medium",
+    "large",
+]
+language_dict = {
+    "": "",
+    "en": "English",
+    "zh": "Chinese",
+    "de": "German",
+    "es": "Spanish",
+    "ru": "Russian",
+    "ko": "Korean",
+    "fr": "French",
+    "ja": "Japanese",
+    "pt": "Portuguese",
+    "tr": "Turkish",
+    "pl": "Polish",
+    "ca": "Catalan",
+    "nl": "Dutch",
+    "ar": "Arabic",
+    "sv": "Swedish",
+    "it": "Italian",
+    "id": "Indonesian",
+    "hi": "Hindi",
+    "fi": "Finnish",
+    "vi": "Vietnamese",
+    "he": "Hebrew",
+    "uk": "Ukrainian",
+    "el": "Greek",
+    "ms": "Malay",
+    "cs": "Czech",
+    "ro": "Romanian",
+    "da": "Danish",
+    "hu": "Hungarian",
+    "ta": "Tamil",
+    "no": "Norwegian",
+    "th": "Thai",
+    "ur": "Urdu",
+    "hr": "Croatian",
+    "bg": "Bulgarian",
+    "lt": "Lithuanian",
+    "la": "Latin",
+    "mi": "Maori",
+    "ml": "Malayalam",
+    "cy": "Welsh",
+    "sk": "Slovak",
+    "te": "Telugu",
+    "fa": "Persian",
+    "lv": "Latvian",
+    "bn": "Bengali",
+    "sr": "Serbian",
+    "az": "Azerbaijani",
+    "sl": "Slovenian",
+    "kn": "Kannada",
+    "et": "Estonian",
+    "mk": "Macedonian",
+    "br": "Breton",
+    "eu": "Basque",
+    "is": "Icelandic",
+    "hy": "Armenian",
+    "ne": "Nepali",
+    "mn": "Mongolian",
+    "bs": "Bosnian",
+    "kk": "Kazakh",
+    "sq": "Albanian",
+    "sw": "Swahili",
+    "gl": "Galician",
+    "mr": "Marathi",
+    "pa": "Punjabi",
+    "si": "Sinhala",
+    "km": "Khmer",
+    "sn": "Shona",
+    "yo": "Yoruba",
+}
+
+
+all_languages = list(language_dict.keys()) + list(language_dict.values())

requirements.txt

@@ -0,0 +1,12 @@
+git+https://github.com/m-bain/whisperx.git
+streamlit
+pandas
+numpy
+torch
+torchaudio
+tqdm
+more-itertools
+transformers>=4.19.0
+ffmpeg-python==0.2.0
+pyannote.audio
+soundfile

segments.json

@@ -0,0 +1,1602 @@
+[
+{
+"text": "Right",
+"start": 1.2872727272727273,
+"end": 1.5085227272727273
+},
+{
+"text": "now",
+"start": 1.5688636363636363,
+"end": 1.77
+},
+{
+"text": "at",
+"start": 2.0113636363636367,
+"end": 2.091818181818182
+},
+{
+"text": "this",
+"start": 2.1119318181818185,
+"end": 2.272840909090909
+},
+{
+"text": "very",
+"start": 2.373409090909091,
+"end": 2.6751136363636365
+},
+{
+"text": "second.",
+"start": 2.7756818181818184,
+"end": 3.0975
+},
+{
+"text": "We're",
+"start": 3.9425641025641025,
+"end": 4.163974358974359
+},
+{
+"text": "in",
+"start": 4.184102564102564,
+"end": 4.244487179487179
+},
+{
+"text": "the",
+"start": 4.28474358974359,
+"end": 4.365256410256411
+},
+{
+"text": "aftermath",
+"start": 4.546410256410256,
+"end": 5.19051282051282
+},
+{
+"text": "of",
+"start": 5.351538461538461,
+"end": 5.432051282051281
+},
+{
+"text": "the",
+"start": 5.472307692307693,
+"end": 5.552820512820513
+},
+{
+"text": "Big",
+"start": 5.572948717948718,
+"end": 5.774230769230769
+},
+{
+"text": "Bang.",
+"start": 5.85474358974359,
+"end": 6.156666666666666
+},
+{
+"text": "Everything",
+"start": 7.201044176706827,
+"end": 7.702048192771084
+},
+{
+"text": "we",
+"start": 7.7621686746987955,
+"end": 7.942530120481928
+},
+{
+"text": "see",
+"start": 8.04273092369478,
+"end": 8.403453815261043
+},
+{
+"text": "in",
+"start": 8.503654618473895,
+"end": 9.205060240963856
+},
+{
+"text": "here",
+"start": 9.345341365461847,
+"end": 9.726104417670683
+},
+{
+"text": "and",
+"start": 10.447550200803214,
+"end": 10.547751004016064
+},
+{
+"text": "taste",
+"start": 10.688032128514056,
+"end": 11.269196787148594
+},
+{
+"text": "and",
+"start": 12.070803212851406,
+"end": 12.191044176706828
+},
+{
+"text": "smell,",
+"start": 12.31128514056225,
+"end": 12.752168674698796
+},
+{
+"text": "and",
+"start": 13.273212851405622,
+"end": 13.373413654618474
+},
+{
+"text": "touch,",
+"start": 13.473614457831324,
+"end": 13.874417670682732
+},
+{
+"text": "is",
+"start": 14.395461847389559,
+"end": 14.49566265060241
+},
+{
+"text": "the",
+"start": 14.53574297188755,
+"end": 14.635943775100401
+},
+{
+"text": "aftermath.",
+"start": 14.736144578313253,
+"end": 15.217108433734941
+},
+{
+"text": "The",
+"start": 17.121672727272728,
+"end": 17.24210909090909
+},
+{
+"text": "Big",
+"start": 17.322400000000002,
+"end": 17.5432
+},
+{
+"text": "Bang",
+"start": 17.643563636363638,
+"end": 18.004872727272726
+},
+{
+"text": "is",
+"start": 18.326036363636362,
+"end": 18.4264
+},
+{
+"text": "really",
+"start": 18.526763636363636,
+"end": 18.908145454545455
+},
+{
+"text": "our",
+"start": 18.92821818181818,
+"end": 19.209236363636364
+},
+{
+"text": "evolving",
+"start": 19.329672727272726,
+"end": 19.931854545454545
+},
+{
+"text": "expanding",
+"start": 20.25301818181818,
+"end": 20.97563636363636
+},
+{
+"text": "universe.",
+"start": 21.176363636363636,
+"end": 21.617963636363637
+},
+{
+"text": "For",
+"start": 24.141747572815536,
+"end": 24.342718446601943
+},
+{
+"text": "us,",
+"start": 24.48339805825243,
+"end": 24.624077669902913
+},
+{
+"text": "mostly",
+"start": 25.327475728155342,
+"end": 25.80980582524272
+},
+{
+"text": "stuck",
+"start": 25.890194174757283,
+"end": 26.171553398058254
+},
+{
+"text": "on",
+"start": 26.25194174757282,
+"end": 26.33233009708738
+},
+{
+"text": "our",
+"start": 26.412718446601943,
+"end": 26.513203883495148
+},
+{
+"text": "rocky",
+"start": 26.59359223300971,
+"end": 26.91514563106796
+},
+{
+"text": "little",
+"start": 26.975436893203884,
+"end": 27.216601941747573
+},
+{
+"text": "planet.",
+"start": 27.276893203883496,
+"end": 27.61854368932039
+},
+{
+"text": "The",
+"start": 28.743076923076924,
+"end": 28.863916083916084
+},
+{
+"text": "view",
+"start": 28.904195804195805,
+"end": 29.125734265734266
+},
+{
+"text": "of",
+"start": 29.166013986013986,
+"end": 29.226433566433567
+},
+{
+"text": "the",
+"start": 29.266713286713287,
+"end": 29.367412587412588
+},
+{
+"text": "universe",
+"start": 29.46811188811189,
+"end": 29.931328671328675
+},
+{
+"text": "begins",
+"start": 30.173006993006997,
+"end": 30.63622377622378
+},
+{
+"text": "with",
+"start": 30.73692307692308,
+"end": 30.8779020979021
+},
+{
+"text": "Earth.",
+"start": 30.978601398601402,
+"end": 31.079300699300703
+},
+{
+"text": "This,",
+"start": 32.70305882352942,
+"end": 32.94588235294118
+},
+{
+"text": "is",
+"start": 33.451764705882354,
+"end": 33.512470588235296
+},
+{
+"text": "Earth.",
+"start": 33.593411764705884,
+"end": 33.75529411764706
+},
+{
+"text": "Silicon",
+"start": 34.74190476190476,
+"end": 35.28476190476191
+},
+{
+"text": "and",
+"start": 35.38529100529101,
+"end": 35.48582010582011
+},
+{
+"text": "oxygen",
+"start": 35.66677248677249,
+"end": 36.04878306878307
+},
+{
+"text": "based,",
+"start": 36.10910052910053,
+"end": 36.410687830687834
+},
+{
+"text": "with",
+"start": 36.873121693121696,
+"end": 36.99375661375662
+},
+{
+"text": "a",
+"start": 37.013862433862435,
+"end": 37.033968253968254
+},
+{
+"text": "metallic",
+"start": 37.07417989417989,
+"end": 37.516507936507935
+},
+{
+"text": "core.",
+"start": 37.59693121693122,
+"end": 37.91862433862434
+},
+{
+"text": "The",
+"start": 39.424,
+"end": 39.525111111111116
+},
+{
+"text": "surface",
+"start": 39.565555555555555,
+"end": 39.99022222222222
+},
+{
+"text": "is",
+"start": 40.111555555555555,
+"end": 40.19244444444445
+},
+{
+"text": "mostly",
+"start": 40.25311111111111,
+"end": 40.617111111111114
+},
+{
+"text": "water.",
+"start": 40.698,
+"end": 40.85977777777778
+},
+{
+"text": "It",
+"start": 42.442009569377994,
+"end": 42.52239234449761
+},
+{
+"text": "teens",
+"start": 42.642966507177036,
+"end": 43.105167464114835
+},
+{
+"text": "with",
+"start": 43.165454545454544,
+"end": 43.346315789473685
+},
+{
+"text": "life",
+"start": 43.4266985645933,
+"end": 43.66784688995215
+},
+{
+"text": "and",
+"start": 43.96928229665072,
+"end": 44.06976076555024
+},
+{
+"text": "rotates",
+"start": 44.17023923444976,
+"end": 44.67263157894737
+},
+{
+"text": "once",
+"start": 44.87358851674641,
+"end": 45.03435406698564
+},
+{
+"text": "every",
+"start": 45.114736842105266,
+"end": 45.2955980861244
+},
+{
+"text": "twenty-four",
+"start": 45.355885167464116,
+"end": 45.878373205741624
+},
+{
+"text": "hours,",
+"start": 45.91856459330143,
+"end": 46.19990430622009
+},
+{
+"text": "while",
+"start": 46.48041666666667,
+"end": 46.66116666666667
+},
+{
+"text": "orbiting",
+"start": 46.801750000000006,
+"end": 47.163250000000005
+},
+{
+"text": "a",
+"start": 47.2235,
+"end": 47.26366666666667
+},
+{
+"text": "star",
+"start": 47.36408333333333,
+"end": 47.72558333333333
+},
+{
+"text": "called",
+"start": 47.826,
+"end": 48.10716666666667
+},
+{
+"text": "the",
+"start": 48.147333333333336,
+"end": 48.24775
+},
+{
+"text": "sun,",
+"start": 48.32808333333334,
+"end": 48.629333333333335
+},
+{
+"text": "every 365",
+"start": 49.01091666666667,
+"end": 49.231833333333334
+},
+{
+"text": "days.",
+"start": 49.272000000000006,
+"end": 49.352333333333334
+},
+{
+"text": "From",
+"start": 51.80240963855422,
+"end": 52.14377510040161
+},
+{
+"text": "what",
+"start": 52.16385542168675,
+"end": 52.5855421686747
+},
+{
+"text": "I",
+"start": 52.60562248995984,
+"end": 52.66586345381526
+},
+{
+"text": "said",
+"start": 53.388755020080325,
+"end": 54.49317269076305
+},
+{
+"text": "here...",
+"start": 54.513253012048196,
+"end": 54.73413654618474
+},
+{
+"text": "This",
+"start": 56.260258620689655,
+"end": 56.360689655172415
+},
+{
+"text": "is",
+"start": 56.40086206896552,
+"end": 56.52137931034483
+},
+{
+"text": "the",
+"start": 56.581637931034486,
+"end": 56.64189655172414
+},
+{
+"text": "Sun,",
+"start": 56.661982758620695,
+"end": 57.22439655172414
+},
+{
+"text": "mostly",
+"start": 57.24448275862069,
+"end": 57.666293103448275
+},
+{
+"text": "hydrogen",
+"start": 57.766724137931035,
+"end": 58.26887931034483
+},
+{
+"text": "and",
+"start": 58.30905172413793,
+"end": 58.38939655172414
+},
+{
+"text": "helium.",
+"start": 58.44965517241379,
+"end": 58.831293103448274
+},
+{
+"text": "Its",
+"start": 60.86,
+"end": 61.10089552238806
+},
+{
+"text": "surface",
+"start": 61.181194029850744,
+"end": 61.502388059701495
+},
+{
+"text": "temperature",
+"start": 61.54253731343284,
+"end": 62.18492537313433
+},
+{
+"text": "is",
+"start": 62.36559701492538,
+"end": 62.48604477611941
+},
+{
+"text": "nearly 10,000",
+"start": 62.50611940298508,
+"end": 62.80723880597015
+},
+{
+"text": "degrees",
+"start": 62.867462686567166,
+"end": 63.32917910447762
+},
+{
+"text": "Fahrenheit.",
+"start": 63.44962686567165,
+"end": 63.951492537313435
+},
+{
+"text": "For",
+"start": 67.54236734693878,
+"end": 67.70302040816327
+},
+{
+"text": "energy,",
+"start": 67.76326530612245,
+"end": 68.12473469387756
+},
+{
+"text": "our",
+"start": 68.48620408163266,
+"end": 68.60669387755102
+},
+{
+"text": "Sun",
+"start": 68.70710204081632,
+"end": 68.96816326530613
+},
+{
+"text": "converged 700",
+"start": 69.04848979591837,
+"end": 70.2734693877551
+},
+{
+"text": "million",
+"start": 70.39395918367347,
+"end": 70.77551020408163
+},
+{
+"text": "tons",
+"start": 70.896,
+"end": 71.19722448979591
+},
+{
+"text": "of",
+"start": 71.2574693877551,
+"end": 71.31771428571429
+},
+{
+"text": "hydrogen",
+"start": 71.33779591836735,
+"end": 71.88
+},
+{
+"text": "into 695",
+"start": 72.34141791044777,
+"end": 73.1644776119403
+},
+{
+"text": "billion",
+"start": 73.96746268656717,
+"end": 74.32880597014926
+},
+{
+"text": "tons",
+"start": 74.40910447761195,
+"end": 74.67007462686568
+},
+{
+"text": "of",
+"start": 74.71022388059703,
+"end": 74.79052238805971
+},
+{
+"text": "helium",
+"start": 74.89089552238806,
+"end": 75.35261194029852
+},
+{
+"text": "every",
+"start": 75.61358208955224,
+"end": 75.91470149253732
+},
+{
+"text": "second.",
+"start": 76.05522388059703,
+"end": 76.41656716417911
+},
+{
+"text": "Sun",
+"start": 77.36006211180124,
+"end": 77.62086956521739
+},
+{
+"text": "is",
+"start": 77.78136645962734,
+"end": 77.82149068322981
+},
+{
+"text": "in",
+"start": 77.84155279503106,
+"end": 77.88167701863354
+},
+{
+"text": "part",
+"start": 77.92180124223603,
+"end": 78.12242236024845
+},
+{
+"text": "of",
+"start": 78.16254658385094,
+"end": 78.22273291925467
+},
+{
+"text": "a",
+"start": 78.26285714285714,
+"end": 78.30298136645963
+},
+{
+"text": "solar",
+"start": 78.3832298136646,
+"end": 78.72428571428571
+},
+{
+"text": "system",
+"start": 78.78447204968944,
+"end": 79.14559006211181
+},
+{
+"text": "formed",
+"start": 79.30608695652174,
+"end": 79.72739130434783
+},
+{
+"text": "around 4.5",
+"start": 79.8076397515528,
+"end": 81.11167701863354
+},
+{
+"text": "billion",
+"start": 81.29223602484473,
+"end": 81.73360248447204
+},
+{
+"text": "years",
+"start": 81.77372670807453,
+"end": 82.01447204968945
+},
+{
+"text": "ago",
+"start": 82.07465838509317,
+"end": 82.31540372670807
+},
+{
+"text": "that",
+"start": 82.69658385093167,
+"end": 82.83701863354037
+},
+{
+"text": "includes",
+"start": 82.8972049689441,
+"end": 83.33857142857143
+},
+{
+"text": "earth",
+"start": 83.47900621118012,
+"end": 83.6595652173913
+},
+{
+"text": "and",
+"start": 83.9405577689243,
+"end": 84.0610358565737
+},
+{
+"text": "seven",
+"start": 84.1614342629482,
+"end": 84.48270916334661
+},
+{
+"text": "other",
+"start": 84.60318725099602,
+"end": 84.82406374501991
+},
+{
+"text": "orbiting",
+"start": 85.06501992031872,
+"end": 85.40637450199203
+},
+{
+"text": "planets",
+"start": 85.48669322709164,
+"end": 85.88828685258964
+},
+{
+"text": "from",
+"start": 86.08908366533865,
+"end": 86.26980079681275
+},
+{
+"text": "Mercury",
+"start": 86.35011952191235,
+"end": 86.81195219123506
+},
+{
+"text": "to",
+"start": 87.67537848605578,
+"end": 87.77577689243029
+},
+{
+"text": "Neptune.",
+"start": 87.85609561752989,
+"end": 88.2978486055777
+},
+{
+"text": "And",
+"start": 89.12161849710984,
+"end": 89.26242774566474
+},
+{
+"text": "its",
+"start": 89.28254335260117,
+"end": 89.34289017341041
+},
+{
+"text": "isn't",
+"start": 89.48369942196533,
+"end": 89.72508670520232
+},
+{
+"text": "a",
+"start": 89.78543352601156,
+"end": 89.8256647398844
+},
+{
+"text": "stationary",
+"start": 89.88601156069365,
+"end": 90.5699421965318
+},
+{
+"text": "system.",
+"start": 90.65040462427746,
+"end": 90.97225433526012
+},
+{
+"text": "Our",
+"start": 93.72036036036036,
+"end": 93.88072072072072
+},
+{
+"text": "solar",
+"start": 93.98094594594595,
+"end": 94.32171171171171
+},
+{
+"text": "system",
+"start": 94.3618018018018,
+"end": 94.68252252252253
+},
+{
+"text": "is",
+"start": 94.96315315315316,
+"end": 95.04333333333334
+},
+{
+"text": "spinning,",
+"start": 95.1636036036036,
+"end": 95.56450450450451
+},
+{
+"text": "flying",
+"start": 96.66698198198199,
+"end": 97.04783783783785
+},
+{
+"text": "through",
+"start": 97.12801801801803,
+"end": 97.36855855855856
+},
+{
+"text": "space",
+"start": 97.46878378378379,
+"end": 97.80954954954956
+},
+{
+"text": "at 134",
+"start": 98.0500900900901,
+"end": 98.13027027027027
+},
+{
+"text": "miles",
+"start": 98.25054054054054,
+"end": 98.41090090090091
+},
+{
+"text": "per",
+"start": 98.47103603603604,
+"end": 98.57126126126127
+},
+{
+"text": "second.",
+"start": 98.6313963963964,
+"end": 98.79175675675677
+},
+{
+"text": "turning",
+"start": 102.6807284768212,
+"end": 103.0619867549669
+},
+{
+"text": "in",
+"start": 103.2225165562914,
+"end": 103.32284768211922
+},
+{
+"text": "circles",
+"start": 103.42317880794702,
+"end": 103.84456953642385
+},
+{
+"text": "as",
+"start": 104.60708609271524,
+"end": 104.68735099337749
+},
+{
+"text": "part",
+"start": 104.7876821192053,
+"end": 104.98834437086093
+},
+{
+"text": "of",
+"start": 105.02847682119206,
+"end": 105.08867549668875
+},
+{
+"text": "a",
+"start": 105.14887417218543,
+"end": 105.168940397351
+},
+{
+"text": "vast",
+"start": 105.28933774834438,
+"end": 105.65052980132451
+},
+{
+"text": "collection",
+"start": 105.75086092715232,
+"end": 106.27258278145696
+},
+{
+"text": "of",
+"start": 106.33278145695364,
+"end": 106.39298013245033
+},
+{
+"text": "stars",
+"start": 106.47324503311259,
+"end": 107.01503311258278
+},
+{
+"text": "and",
+"start": 107.11536423841059,
+"end": 107.19562913907285
+},
+{
+"text": "star",
+"start": 107.29596026490066,
+"end": 107.63708609271524
+},
+{
+"text": "systems.",
+"start": 107.71735099337748,
+"end": 108.1387417218543
+},
+{
+"text": "There",
+"start": 109.02,
+"end": 109.12033557046979
+},
+{
+"text": "may",
+"start": 109.14040268456375,
+"end": 109.30093959731543
+},
+{
+"text": "be 200",
+"start": 109.3611409395973,
+"end": 109.82268456375839
+},
+{
+"text": "billion",
+"start": 110.58523489932885,
+"end": 111.00664429530201
+},
+{
+"text": "stars",
+"start": 111.1069798657718,
+"end": 111.54845637583892
+},
+{
+"text": "in",
+"start": 111.72906040268457,
+"end": 111.78926174496644
+},
+{
+"text": "this",
+"start": 111.8093288590604,
+"end": 111.94979865771812
+},
+{
+"text": "collection",
+"start": 111.98993288590604,
+"end": 112.511677852349
+},
+{
+"text": "called",
+"start": 112.61201342281879,
+"end": 112.93308724832215
+},
+{
+"text": "the",
+"start": 112.99328859060402,
+"end": 113.07355704697986
+},
+{
+"text": "Milky",
+"start": 113.17389261744967,
+"end": 113.59530201342282
+},
+{
+"text": "Way",
+"start": 113.6555033557047,
+"end": 113.89630872483221
+},
+{
+"text": "Galaxy.",
+"start": 114.03677852348993,
+"end": 114.55852348993288
+},
+{
+"text": "And",
+"start": 115.60069204152248,
+"end": 115.68096885813148
+},
+{
+"text": "estimated 6",
+"start": 115.78131487889273,
+"end": 116.24290657439445
+},
+{
+"text": "billion",
+"start": 116.92525951557093,
+"end": 117.3667820069204
+},
+{
+"text": "of",
+"start": 117.38685121107265,
+"end": 117.4470588235294
+},
+{
+"text": "those",
+"start": 117.4871972318339,
+"end": 117.68788927335639
+},
+{
+"text": "stars",
+"start": 117.74809688581314,
+"end": 118.14948096885813
+},
+{
+"text": "with",
+"start": 118.35017301038062,
+"end": 118.49065743944635
+},
+{
+"text": "planetary",
+"start": 118.5910034602076,
+"end": 119.25328719723183
+},
+{
+"text": "systems",
+"start": 119.33356401384081,
+"end": 119.7750865051903
+},
+{
+"text": "like",
+"start": 120.07612456747404,
+"end": 120.25674740484428
+},
+{
+"text": "ours.",
+"start": 120.41730103806228,
+"end": 120.61799307958476
+},
+{
+"text": "Our",
+"start": 122.18071895424836,
+"end": 122.28104575163398
+},
+{
+"text": "Solar",
+"start": 122.34124183006536,
+"end": 122.68235294117646
+},
+{
+"text": "System",
+"start": 122.74254901960784,
+"end": 123.08366013071895
+},
+{
+"text": "orbits",
+"start": 123.2843137254902,
+"end": 123.58529411764705
+},
+{
+"text": "the",
+"start": 123.64549019607843,
+"end": 123.76588235294118
+},
+{
+"text": "center",
+"start": 123.82607843137254,
+"end": 124.16718954248365
+},
+{
+"text": "of",
+"start": 124.32771241830065,
+"end": 124.38790849673202
+},
+{
+"text": "the",
+"start": 124.42803921568627,
+"end": 124.50830065359476
+},
+{
+"text": "Milky",
+"start": 124.54843137254902,
+"end": 124.84941176470588
+},
+{
+"text": "Way,",
+"start": 124.92967320261437,
+"end": 125.23065359477124
+},
+{
+"text": "on",
+"start": 125.89281045751633,
+"end": 125.97307189542484
+},
+{
+"text": "one",
+"start": 126.07339869281046,
+"end": 126.17372549019608
+},
+{
+"text": "of",
+"start": 126.21385620915032,
+"end": 126.25398692810457
+},
+{
+"text": "it's",
+"start": 126.33424836601307,
+"end": 126.4546405228758
+},
+{
+"text": "outer",
+"start": 126.63522875816993,
+"end": 126.89607843137254
+},
+{
+"text": "arms.",
+"start": 127.17699346405229,
+"end": 127.41777777777777
+},
+{
+"text": "The",
+"start": 131.10209497206702,
+"end": 131.20216480446928
+},
+{
+"text": "Milky",
+"start": 131.24219273743017,
+"end": 131.56241620111732
+},
+{
+"text": "Way",
+"start": 131.6024441340782,
+"end": 131.88263966480446
+},
+{
+"text": "is",
+"start": 131.90265363128492,
+"end": 131.94268156424582
+},
+{
+"text": "a",
+"start": 132.16283519553073,
+"end": 132.20286312849163
+},
+{
+"text": "snow",
+"start": 132.22287709497206,
+"end": 132.42301675977654
+},
+{
+"text": "of 235",
+"start": 132.4630446927374,
+"end": 132.5030726256983
+},
+{
+"text": "billion",
+"start": 132.5431005586592,
+"end": 132.90335195530724
+},
+{
+"text": "galaxies",
+"start": 132.9233659217877,
+"end": 133.24358938547485
+},
+{
+"text": "that",
+"start": 133.2636033519553,
+"end": 133.40370111731843
+},
+{
+"text": "predicts",
+"start": 133.42371508379887,
+"end": 133.8239944134078
+},
+{
+"text": "the",
+"start": 133.9040502793296,
+"end": 134.00412011173185
+},
+{
+"text": "unique",
+"start": 134.02413407821228,
+"end": 134.3643715083799
+},
+{
+"text": "if",
+"start": 158.08481751824817,
+"end": 158.1851824817518
+},
+{
+"text": "the",
+"start": 158.22532846715328,
+"end": 158.3256934306569
+},
+{
+"text": "universe",
+"start": 158.40598540145984,
+"end": 158.86766423357665
+},
+{
+"text": "is",
+"start": 158.98810218978102,
+"end": 159.08846715328465
+},
+{
+"text": "expanding",
+"start": 159.14868613138685,
+"end": 159.69065693430656
+},
+{
+"text": "then",
+"start": 160.3129197080292,
+"end": 160.43335766423357
+},
+{
+"text": "it",
+"start": 160.47350364963503,
+"end": 160.5337226277372
+},
+{
+"text": "used",
+"start": 160.61401459854014,
+"end": 160.77459854014597
+},
+{
+"text": "to",
+"start": 160.7946715328467,
+"end": 160.87496350364964
+},
+{
+"text": "be",
+"start": 160.91510948905108,
+"end": 161.03554744525547
+},
+{
+"text": "smaller",
+"start": 161.11583941605838,
+"end": 161.49722627737225
+},
+{
+"text": "much",
+"start": 163.04609374999998,
+"end": 163.28796875
+},
+{
+"text": "smaller",
+"start": 163.3484375,
+"end": 163.73140625
+},
+{
+"text": "in",
+"start": 165.54275590551183,
+"end": 165.62307086614175
+},
+{
+"text": "fact",
+"start": 165.72346456692912,
+"end": 166.02464566929135
+},
+{
+"text": "if",
+"start": 166.46637795275592,
+"end": 166.54669291338584
+},
+{
+"text": "we",
+"start": 166.5868503937008,
+"end": 166.70732283464568
+},
+{
+"text": "went",
+"start": 166.74748031496063,
+"end": 166.90811023622047
+},
+{
+"text": "back",
+"start": 166.9884251968504,
+"end": 167.2092913385827
+},
+{
+"text": "in",
+"start": 167.26952755905512,
+"end": 167.34984251968504
+},
+{
+"text": "time",
+"start": 167.43015748031496,
+"end": 167.79157480314962
+},
+{
+"text": "we",
+"start": 168.37385826771654,
+"end": 168.47425196850395
+},
+{
+"text": "could",
+"start": 168.5144094488189,
+"end": 168.67503937007874
+},
+{
+"text": "watch",
+"start": 168.75535433070866,
+"end": 169.05653543307088
+},
+{
+"text": "it",
+"start": 169.09669291338582,
+"end": 169.17700787401574
+},
+{
+"text": "shrink",
+"start": 169.3175590551181,
+"end": 169.57858267716534
+},
+{
+"text": "back",
+"start": 175.1248,
+"end": 175.3654857142857
+},
+{
+"text": "far",
+"start": 175.42565714285715,
+"end": 175.66634285714284
+},
+{
+"text": "enough",
+"start": 175.70645714285715,
+"end": 175.98725714285715
+},
+{
+"text": "and",
+"start": 176.72937142857143,
+"end": 176.8096
+},
+{
+"text": "the",
+"start": 176.84971428571427,
+"end": 176.92994285714283
+},
+{
+"text": "universe",
+"start": 177.03022857142855,
+"end": 177.41131428571427
+},
+{
+"text": "would",
+"start": 177.4714857142857,
+"end": 177.63194285714283
+},
+{
+"text": "be",
+"start": 177.652,
+"end": 177.7522857142857
+},
+{
+"text": "smaller",
+"start": 177.83251428571427,
+"end": 178.23365714285714
+},
+{
+"text": "than",
+"start": 178.27377142857142,
+"end": 178.43422857142855
+},
+{
+"text": "a",
+"start": 178.47434285714283,
+"end": 178.49439999999998
+},
+{
+"text": "galaxy",
+"start": 178.57462857142855,
+"end": 179.07605714285714
+},
+{
+"text": "back..and",
+"start": 180.9022797927461,
+"end": 181.76673575129533
+},
+{
+"text": "the",
+"start": 181.78683937823834,
+"end": 181.86725388601036
+},
+{
+"text": "universe",
+"start": 181.9677720207254,
+"end": 182.32963730569946
+},
+{
+"text": "is",
+"start": 182.3899481865285,
+"end": 182.4502590673575
+},
+{
+"text": "smaller",
+"start": 182.51056994818651,
+"end": 182.87243523316062
+},
+{
+"text": "than",
+"start": 182.91264248704664,
+"end": 183.05336787564767
+},
+{
+"text": "our",
+"start": 183.13378238341969,
+"end": 183.23430051813472
+},
+{
+"text": "solar",
+"start": 183.31471502590674,
+"end": 183.6162694300518
+},
+{
+"text": "system",
+"start": 183.67658031088084,
+"end": 183.9580310880829
+},
+{
+"text": "inely",
+"start": 184.54080321285142,
+"end": 184.82192771084337
+},
+{
+"text": "earn",
+"start": 184.9223293172691,
+"end": 185.00265060240963
+},
+{
+"text": "more.",
+"start": 185.06289156626505,
+"end": 185.14321285140562
+},
+{
+"text": "Fast",
+"start": 189.34,
+"end": 189.46363636363637
+},
+{
+"text": "enjoyment.",
+"start": 189.48424242424244,
+"end": 189.95818181818183
+},
+{
+"text": "Faster",
+"start": 190.08015151515153,
+"end": 190.22050505050507
+},
+{
+"text": "back",
+"start": 191.40348484848485,
+"end": 191.5438383838384
+},
+{
+"text": "and",
+"start": 191.62404040404041,
+"end": 191.74434343434345
+},
+{
+"text": "everything",
+"start": 191.76439393939395,
+"end": 194.11030303030304
+},
+{
+"text": "that",
+"start": 198.14260869565217,
+"end": 198.4672463768116
+},
+{
+"text": "exists",
+"start": 198.54840579710145,
+"end": 198.67014492753626
+},
+{
+"text": "fits",
+"start": 198.71072463768118,
+"end": 198.87304347826088
+},
+{
+"text": "inside",
+"start": 198.89333333333335,
+"end": 199.01507246376812
+},
+{
+"text": "a",
+"start": 199.03536231884058,
+"end": 199.05565217391305
+},
+{
+"text": "stadium.",
+"start": 199.3800638977636,
+"end": 199.70108626198083
+},
+{
+"text": "our",
+"start": 199.78134185303514,
+"end": 200.122428115016
+},
+{
+"text": "coffee",
+"start": 200.14249201277957,
+"end": 200.4835782747604
+},
+{
+"text": "cup.",
+"start": 200.50364217252397,
+"end": 200.5638338658147
+},
+{
+"text": "adventure",
+"start": 205.94315789473686,
+"end": 206.2058947368421
+},
+{
+"text": "switch",
+"start": 207.27705263157895,
+"end": 207.51957894736842
+},
+{
+"text": "All",
+"start": 207.56,
+"end": 207.74346153846153
+},
+{
+"text": "stands",
+"start": 207.76384615384615,
+"end": 208.02884615384616
+},
+{
+"text": "at.",
+"start": 208.2326923076923,
+"end": 208.33461538461538
+},
+{
+"text": "G",
+"start": 210.18423913043478,
+"end": 210.20429347826087
+},
+{
+"text": "This",
+"start": 219.0646288209607,
+"end": 219.3056768558952
+},
+{
+"text": "was",
+"start": 219.52663755458516,
+"end": 219.6471615720524
+},
+{
+"text": "how",
+"start": 219.707423580786,
+"end": 219.86812227074236
+},
+{
+"text": "it",
+"start": 219.90829694323145,
+"end": 219.96855895196506
+},
+{
+"text": "all",
+"start": 220.10917030567686,
+"end": 220.24978165938865
+},
+{
+"text": "began.",
+"start": 220.35021834061135,
+"end": 220.69170305676855
+},
+{
+"text": "Performance",
+"start": 222.7410218978102,
+"end": 223.3655474452555
+},
+{
+"text": "The",
+"start": 225.520323943662,
+"end": 225.58044542253523
+},
+{
+"text": "Big",
+"start": 225.62052640845073,
+"end": 225.76080985915493
+},
+{
+"text": "Bang",
+"start": 225.78085035211268,
+"end": 225.86101232394367
+},
+{
+"text": "ain't",
+"start": 225.88105281690142,
+"end": 226.12153873239438
+},
+{
+"text": "the",
+"start": 226.18166021126763,
+"end": 226.30190316901408
+},
+{
+"text": "big",
+"start": 226.36202464788732,
+"end": 226.6425915492958
+},
+{
+"text": "bang.",
+"start": 226.782875,
+"end": 227.14360387323944
+}
+]

setup.py

@@ -0,0 +1,28 @@
+import os
+
+import pkg_resources
+from setuptools import setup, find_packages
+
+setup(
+    name="whisperx",
+    py_modules=["whisperx"],
+    version="1.0",
+    description="Time-Accurate Automatic Speech Recognition using Whisper.",
+    readme="README.md",
+    python_requires=">=3.7",
+    author="Max Bain",
+    url="https://github.com/m-bain/whisperx",
+    license="MIT",
+    packages=find_packages(exclude=["tests*"]),
+    install_requires=[
+        str(r)
+        for r in pkg_resources.parse_requirements(
+            open(os.path.join(os.path.dirname(__file__), "requirements.txt"))
+        )
+    ],
+    entry_points = {
+        'console_scripts': ['whisperx=whisperx.transcribe:cli'],
+    },
+    include_package_data=True,
+    extras_require={'dev': ['pytest']},
+)

transcription.json

@@ -0,0 +1,922 @@
+[
+    {
+        "id": 0,
+        "seek": 0,
+        "start": 0.0,
+        "end": 3.54,
+        "text": " Right now at this very second.",
+        "tokens": [
+            1779,
+            586,
+            412,
+            341,
+            588,
+            1150,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6253367182034165,
+        "compression_ratio": 1.494047619047619,
+        "no_speech_prob": 0.5233597159385681
+    },
+    {
+        "id": 1,
+        "seek": 0,
+        "start": 3.54,
+        "end": 6.68,
+        "text": " We're in the aftermath of the Big Bang.",
+        "tokens": [
+            492,
+            434,
+            294,
+            264,
+            34095,
+            295,
+            264,
+            5429,
+            11538,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6253367182034165,
+        "compression_ratio": 1.494047619047619,
+        "no_speech_prob": 0.5233597159385681
+    },
+    {
+        "id": 2,
+        "seek": 0,
+        "start": 6.68,
+        "end": 16.66,
+        "text": " Everything we see in here and taste and smell, and touch, is the aftermath.",
+        "tokens": [
+            5471,
+            321,
+            536,
+            294,
+            510,
+            293,
+            3939,
+            293,
+            4316,
+            11,
+            293,
+            2557,
+            11,
+            307,
+            264,
+            34095,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6253367182034165,
+        "compression_ratio": 1.494047619047619,
+        "no_speech_prob": 0.5233597159385681
+    },
+    {
+        "id": 3,
+        "seek": 0,
+        "start": 16.66,
+        "end": 22.18,
+        "text": " The Big Bang is really our evolving expanding universe.",
+        "tokens": [
+            440,
+            5429,
+            11538,
+            307,
+            534,
+            527,
+            21085,
+            14702,
+            6445,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6253367182034165,
+        "compression_ratio": 1.494047619047619,
+        "no_speech_prob": 0.5233597159385681
+    },
+    {
+        "id": 4,
+        "seek": 0,
+        "start": 23.78,
+        "end": 27.92,
+        "text": " For us, mostly stuck on our rocky little planet.",
+        "tokens": [
+            1171,
+            505,
+            11,
+            5240,
+            5541,
+            322,
+            527,
+            33301,
+            707,
+            5054,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6253367182034165,
+        "compression_ratio": 1.494047619047619,
+        "no_speech_prob": 0.5233597159385681
+    },
+    {
+        "id": 5,
+        "seek": 2792,
+        "start": 28.3,
+        "end": 31.180000000000003,
+        "text": " The view of the universe begins with Earth.",
+        "tokens": [
+            440,
+            1910,
+            295,
+            264,
+            6445,
+            7338,
+            365,
+            4755,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.9778916732124661,
+        "compression_ratio": 1.4180790960451977,
+        "no_speech_prob": 0.25073713064193726
+    },
+    {
+        "id": 6,
+        "seek": 2792,
+        "start": 32.440000000000005,
+        "end": 34.160000000000004,
+        "text": " This, is Earth.",
+        "tokens": [
+            639,
+            11,
+            307,
+            4755,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.9778916732124661,
+        "compression_ratio": 1.4180790960451977,
+        "no_speech_prob": 0.25073713064193726
+    },
+    {
+        "id": 7,
+        "seek": 2792,
+        "start": 34.38,
+        "end": 38.18,
+        "text": " Silicon and oxygen based, with a metallic core.",
+        "tokens": [
+            25351,
+            293,
+            9169,
+            2361,
+            11,
+            365,
+            257,
+            25759,
+            4965,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.9778916732124661,
+        "compression_ratio": 1.4180790960451977,
+        "no_speech_prob": 0.25073713064193726
+    },
+    {
+        "id": 8,
+        "seek": 2792,
+        "start": 39.06,
+        "end": 40.88,
+        "text": " The surface is mostly water.",
+        "tokens": [
+            440,
+            3753,
+            307,
+            5240,
+            1281,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.9778916732124661,
+        "compression_ratio": 1.4180790960451977,
+        "no_speech_prob": 0.25073713064193726
+    },
+    {
+        "id": 9,
+        "seek": 2792,
+        "start": 42.02,
+        "end": 46.22,
+        "text": " It teens with life and rotates once every twenty-four hours,",
+        "tokens": [
+            467,
+            24849,
+            365,
+            993,
+            293,
+            42133,
+            1564,
+            633,
+            7699,
+            12,
+            23251,
+            2496,
+            11
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.9778916732124661,
+        "compression_ratio": 1.4180790960451977,
+        "no_speech_prob": 0.25073713064193726
+    },
+    {
+        "id": 10,
+        "seek": 2792,
+        "start": 46.38,
+        "end": 51.2,
+        "text": " while orbiting a star called the sun, every 365 days.",
+        "tokens": [
+            1339,
+            48985,
+            257,
+            3543,
+            1219,
+            264,
+            3295,
+            11,
+            633,
+            22046,
+            1708,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.9778916732124661,
+        "compression_ratio": 1.4180790960451977,
+        "no_speech_prob": 0.25073713064193726
+    },
+    {
+        "id": 11,
+        "seek": 5120,
+        "start": 51.2,
+        "end": 56.2,
+        "text": " From what I said here...",
+        "tokens": [
+            3358,
+            437,
+            286,
+            848,
+            510,
+            485
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -1.3197117789846953,
+        "compression_ratio": 1.3988095238095237,
+        "no_speech_prob": 0.273966521024704
+    },
+    {
+        "id": 12,
+        "seek": 5120,
+        "start": 56.120000000000005,
+        "end": 60.86,
+        "text": " This is the Sun, mostly hydrogen and helium.",
+        "tokens": [
+            639,
+            307,
+            264,
+            6163,
+            11,
+            5240,
+            12697,
+            293,
+            40175,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -1.3197117789846953,
+        "compression_ratio": 1.3988095238095237,
+        "no_speech_prob": 0.273966521024704
+    },
+    {
+        "id": 13,
+        "seek": 5120,
+        "start": 60.86,
+        "end": 66.24000000000001,
+        "text": " Its surface temperature is nearly 10,000 degrees Fahrenheit.",
+        "tokens": [
+            6953,
+            3753,
+            4292,
+            307,
+            6217,
+            1266,
+            11,
+            1360,
+            5310,
+            31199,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -1.3197117789846953,
+        "compression_ratio": 1.3988095238095237,
+        "no_speech_prob": 0.273966521024704
+    },
+    {
+        "id": 14,
+        "seek": 5120,
+        "start": 66.96000000000001,
+        "end": 71.88,
+        "text": " For energy, our Sun converged 700 million tons of hydrogen",
+        "tokens": [
+            1171,
+            2281,
+            11,
+            527,
+            6163,
+            9652,
+            3004,
+            15204,
+            2459,
+            9131,
+            295,
+            12697
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -1.3197117789846953,
+        "compression_ratio": 1.3988095238095237,
+        "no_speech_prob": 0.273966521024704
+    },
+    {
+        "id": 15,
+        "seek": 5120,
+        "start": 71.96000000000001,
+        "end": 77.34,
+        "text": " into 695 billion tons of helium every second.",
+        "tokens": [
+            666,
+            1386,
+            15718,
+            5218,
+            9131,
+            295,
+            40175,
+            633,
+            1150,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -1.3197117789846953,
+        "compression_ratio": 1.3988095238095237,
+        "no_speech_prob": 0.273966521024704
+    },
+    {
+        "id": 16,
+        "seek": 7734,
+        "start": 77.34,
+        "end": 83.8,
+        "text": " Sun is in part of a solar system formed around 4.5 billion years ago that includes earth",
+        "tokens": [
+            6163,
+            307,
+            294,
+            644,
+            295,
+            257,
+            7936,
+            1185,
+            8693,
+            926,
+            1017,
+            13,
+            20,
+            5218,
+            924,
+            2057,
+            300,
+            5974,
+            4120
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.7630057561965216,
+        "compression_ratio": 1.4043715846994536,
+        "no_speech_prob": 0.3166518807411194
+    },
+    {
+        "id": 17,
+        "seek": 7734,
+        "start": 83.8,
+        "end": 88.84,
+        "text": " and seven other orbiting planets from Mercury to Neptune.",
+        "tokens": [
+            293,
+            3407,
+            661,
+            48985,
+            15126,
+            490,
+            31780,
+            281,
+            49527,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.7630057561965216,
+        "compression_ratio": 1.4043715846994536,
+        "no_speech_prob": 0.3166518807411194
+    },
+    {
+        "id": 18,
+        "seek": 7734,
+        "start": 88.84,
+        "end": 92.32000000000001,
+        "text": " And its isn't a stationary system.",
+        "tokens": [
+            400,
+            1080,
+            1943,
+            380,
+            257,
+            30452,
+            1185,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.7630057561965216,
+        "compression_ratio": 1.4043715846994536,
+        "no_speech_prob": 0.3166518807411194
+    },
+    {
+        "id": 19,
+        "seek": 7734,
+        "start": 93.56,
+        "end": 102.46000000000001,
+        "text": " Our solar system is spinning, flying through space at 134 miles per second.",
+        "tokens": [
+            2621,
+            7936,
+            1185,
+            307,
+            15640,
+            11,
+            7137,
+            807,
+            1901,
+            412,
+            3705,
+            19,
+            6193,
+            680,
+            1150,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.7630057561965216,
+        "compression_ratio": 1.4043715846994536,
+        "no_speech_prob": 0.3166518807411194
+    },
+    {
+        "id": 20,
+        "seek": 10246,
+        "start": 102.46,
+        "end": 108.52,
+        "text": " turning in circles as part of a vast collection of stars and star systems.",
+        "tokens": [
+            6246,
+            294,
+            13040,
+            382,
+            644,
+            295,
+            257,
+            8369,
+            5765,
+            295,
+            6105,
+            293,
+            3543,
+            3652,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6545037693447537,
+        "compression_ratio": 1.5532994923857868,
+        "no_speech_prob": 0.09585275501012802
+    },
+    {
+        "id": 21,
+        "seek": 10246,
+        "start": 109.02,
+        "end": 115.0,
+        "text": " There may be 200 billion stars in this collection called the Milky Way Galaxy.",
+        "tokens": [
+            821,
+            815,
+            312,
+            2331,
+            5218,
+            6105,
+            294,
+            341,
+            5765,
+            1219,
+            264,
+            38465,
+            9558,
+            13520,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6545037693447537,
+        "compression_ratio": 1.5532994923857868,
+        "no_speech_prob": 0.09585275501012802
+    },
+    {
+        "id": 22,
+        "seek": 10246,
+        "start": 115.39999999999999,
+        "end": 121.19999999999999,
+        "text": " And estimated 6 billion of those stars with planetary systems like ours.",
+        "tokens": [
+            400,
+            14109,
+            1386,
+            5218,
+            295,
+            729,
+            6105,
+            365,
+            35788,
+            3652,
+            411,
+            11896,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6545037693447537,
+        "compression_ratio": 1.5532994923857868,
+        "no_speech_prob": 0.09585275501012802
+    },
+    {
+        "id": 23,
+        "seek": 10246,
+        "start": 121.96,
+        "end": 128.1,
+        "text": " Our Solar System orbits the center of the Milky Way, on one of it's outer arms.",
+        "tokens": [
+            2621,
+            22385,
+            8910,
+            43522,
+            264,
+            3056,
+            295,
+            264,
+            38465,
+            9558,
+            11,
+            322,
+            472,
+            295,
+            309,
+            311,
+            10847,
+            5812,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.6545037693447537,
+        "compression_ratio": 1.5532994923857868,
+        "no_speech_prob": 0.09585275501012802
+    },
+    {
+        "id": 24,
+        "seek": 12810,
+        "start": 128.1,
+        "end": 156.76,
+        "text": " The Milky Way is a snow of 235 billion galaxies that predicts the unique",
+        "tokens": [
+            440,
+            38465,
+            9558,
+            307,
+            257,
+            5756,
+            295,
+            6673,
+            20,
+            5218,
+            28755,
+            300,
+            6069,
+            82,
+            264,
+            3845
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -3.183812141418457,
+        "compression_ratio": 0.96,
+        "no_speech_prob": 0.2284129559993744
+    },
+    {
+        "id": 25,
+        "seek": 15676,
+        "start": 156.76,
+        "end": 162.26,
+        "text": " if the universe is expanding then it used to be smaller",
+        "tokens": [
+            498,
+            264,
+            6445,
+            307,
+            14702,
+            550,
+            309,
+            1143,
+            281,
+            312,
+            4356
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.819732165727459,
+        "compression_ratio": 1.7013888888888888,
+        "no_speech_prob": 0.3402792513370514
+    },
+    {
+        "id": 26,
+        "seek": 15676,
+        "start": 162.26,
+        "end": 164.84,
+        "text": " much smaller",
+        "tokens": [
+            709,
+            4356
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.819732165727459,
+        "compression_ratio": 1.7013888888888888,
+        "no_speech_prob": 0.3402792513370514
+    },
+    {
+        "id": 27,
+        "seek": 15676,
+        "start": 164.84,
+        "end": 169.94,
+        "text": " in fact if we went back in time we could watch it shrink",
+        "tokens": [
+            294,
+            1186,
+            498,
+            321,
+            1437,
+            646,
+            294,
+            565,
+            321,
+            727,
+            1159,
+            309,
+            23060
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.819732165727459,
+        "compression_ratio": 1.7013888888888888,
+        "no_speech_prob": 0.3402792513370514
+    },
+    {
+        "id": 28,
+        "seek": 15676,
+        "start": 173.44,
+        "end": 180.45999999999998,
+        "text": " back far enough and the universe would be smaller than a galaxy",
+        "tokens": [
+            646,
+            1400,
+            1547,
+            293,
+            264,
+            6445,
+            576,
+            312,
+            4356,
+            813,
+            257,
+            17639
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.819732165727459,
+        "compression_ratio": 1.7013888888888888,
+        "no_speech_prob": 0.3402792513370514
+    },
+    {
+        "id": 29,
+        "seek": 15676,
+        "start": 180.45999999999998,
+        "end": 184.34,
+        "text": " back..and the universe is smaller than our solar system",
+        "tokens": [
+            646,
+            353,
+            474,
+            264,
+            6445,
+            307,
+            4356,
+            813,
+            527,
+            7936,
+            1185
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -0.819732165727459,
+        "compression_ratio": 1.7013888888888888,
+        "no_speech_prob": 0.3402792513370514
+    },
+    {
+        "id": 30,
+        "seek": 18434,
+        "start": 184.34,
+        "end": 189.34,
+        "text": "inely earn more.",
+        "tokens": [
+            33592,
+            6012,
+            544,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 31,
+        "seek": 18434,
+        "start": 185.28,
+        "end": 190.02,
+        "text": " Fast enjoyment.",
+        "tokens": [
+            15968,
+            32013,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 32,
+        "seek": 18434,
+        "start": 187.16,
+        "end": 197.96,
+        "text": " Faster back and everything",
+        "tokens": [
+            46665,
+            646,
+            293,
+            1203
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 33,
+        "seek": 18434,
+        "start": 188.18,
+        "end": 199.36,
+        "text": " that exists fits inside a",
+        "tokens": [
+            300,
+            8198,
+            9001,
+            1854,
+            257
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 34,
+        "seek": 18434,
+        "start": 194.4,
+        "end": 205.64000000000001,
+        "text": " stadium. our coffee cup.",
+        "tokens": [
+            18585,
+            13,
+            527,
+            4982,
+            4414,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 35,
+        "seek": 18434,
+        "start": 199.54,
+        "end": 207.56,
+        "text": " adventure switch",
+        "tokens": [
+            9868,
+            3679
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 36,
+        "seek": 18434,
+        "start": 205.1,
+        "end": 208.62,
+        "text": " All stands at.",
+        "tokens": [
+            1057,
+            7382,
+            412,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -4.394529169256037,
+        "compression_ratio": 1.2456140350877194,
+        "no_speech_prob": 0.16134849190711975
+    },
+    {
+        "id": 37,
+        "seek": 20862,
+        "start": 208.62,
+        "end": 216.0,
+        "text": " G",
+        "tokens": [
+            460
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -3.1060187395881202,
+        "compression_ratio": 0.8333333333333334,
+        "no_speech_prob": 0.1563536673784256
+    },
+    {
+        "id": 38,
+        "seek": 20862,
+        "start": 218.0,
+        "end": 222.6,
+        "text": " This was how it all began.",
+        "tokens": [
+            639,
+            390,
+            577,
+            309,
+            439,
+            4283,
+            13
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -3.1060187395881202,
+        "compression_ratio": 0.8333333333333334,
+        "no_speech_prob": 0.1563536673784256
+    },
+    {
+        "id": 39,
+        "seek": 20862,
+        "start": 222.6,
+        "end": 225.36,
+        "text": " Performance",
+        "tokens": [
+            25047
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -3.1060187395881202,
+        "compression_ratio": 0.8333333333333334,
+        "no_speech_prob": 0.1563536673784256
+    },
+    {
+        "id": 40,
+        "seek": 22536,
+        "start": 225.36,
+        "end": 228.24,
+        "text": " The Big Bang ain't the big bang.",
+        "tokens": [
+            50364,
+            440,
+            5429,
+            11538,
+            7862,
+            380,
+            264,
+            955,
+            8550,
+            13,
+            50508
+        ],
+        "temperature": 1.0,
+        "avg_logprob": -1.9082762400309246,
+        "compression_ratio": 0.8888888888888888,
+        "no_speech_prob": 0.19741153717041016
+    }
+]

utils.py

@@ -0,0 +1,83 @@
+import whisperx as whisper
+
+from deep_translator import GoogleTranslator
+import os
+from whisperx.utils import write_vtt, write_srt, write_ass, write_tsv, write_txt
+
+
+def detect_language(filename, model):
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(file=filename)
+    audio = whisper.pad_or_trim(audio)
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+    return {"detected_language": max(probs, key=probs.get)}
+
+
+def translate_to_english(transcription, json=False):
+    if json:
+        for text in transcription:
+            text["text"] = GoogleTranslator(source="auto", target="en").translate(
+                text["text"]
+            )
+    else:
+
+        for text in transcription["segments"]:
+            text["text"] = GoogleTranslator(source="auto", target="en").translate(
+                text["text"]
+            )
+    return transcription
+
+
+def write(filename, dtype, result_aligned):
+
+    if dtype == "vtt":
+        with open(
+            os.path.join(".", os.path.splitext(filename)[0] + ".vtt"), "w"
+        ) as vtt:
+            write_vtt(result_aligned["segments"], file=vtt)
+    if dtype == "srt":
+        with open(
+            os.path.join(".", os.path.splitext(filename)[0] + ".srt"), "w"
+        ) as srt:
+            write_srt(result_aligned["segments"], file=srt)
+    if dtype == "ass":
+        with open(
+            os.path.join(".", os.path.splitext(filename)[0] + ".ass"), "w"
+        ) as ass:
+            write_ass(result_aligned["segments"], file=ass)
+    if dtype == "tsv":
+        with open(
+            os.path.join(".", os.path.splitext(filename)[0] + ".tsv"), "w"
+        ) as tsv:
+            write_tsv(result_aligned["segments"], file=tsv)
+    if dtype == "plain text":
+        print("here")
+        print(filename)
+        with open(
+            os.path.join(".", os.path.splitext(filename)[0] + ".txt"), "w"
+        ) as txt:
+            write_txt(result_aligned["segments"], file=txt)
+
+
+def read(filename, transc):
+    if transc == "plain text":
+        transc = "txt"
+    filename = filename.split(".")[0]
+    print(filename)
+    with open(f"{filename}.{transc}", encoding="utf-8") as f:
+        content = f.readlines()
+    content = " ".join(z for z in content)
+    return content
+
+
+from constants import language_dict
+
+
+def get_key(val):
+    for key, value in language_dict.items():
+        if val == value:
+            return key
+    return "Key not found"