diff --git a/accompanist/collection/recognizer.py b/accompanist/collection/recognizer.py index 265c30b..b25d3f3 100644 --- a/accompanist/collection/recognizer.py +++ b/accompanist/collection/recognizer.py @@ -1,19 +1,16 @@ from functools import lru_cache +from pathlib import Path from typing import List import whisper -import yaml -class Timestamper: - def __init__(self, data_path: str) -> None: - self.data_path = data_path +class LyricsTimestamper: + MODEL_TYPE = "tiny" + DEVICE = "cuda" - with open(self.data_path, "r") as config: - model_cfg = yaml.safe_load(config) - model_type = model_cfg["type"] - device = model_cfg["device"] - self.model = whisper.load_model(model_type).to(device) + def __init__(self) -> None: + self.model = whisper.load_model(self.MODEL_TYPE).to(self.DEVICE) def _levenshtein_distance(self, s1: str, s2: str) -> int: @lru_cache(maxsize=None) @@ -27,18 +24,20 @@ def helper(i, j): return helper(len(s1), len(s2)) - def get_line_timestamps( - self, path_mp3: str, path_text: str - ) -> List[dict[str, str]]: - with open(path_text, "r") as f: - text_lines = f.readlines() + def get_karaoke_lyrics(self, path_mp3: Path, lyrics: str) -> List[dict[str, str]]: + # TODO: standardize lyrics preprocessing + lyrics_lines = [ + line.strip() + for line in lyrics.split("\n") + if line.strip() and not line.startswith("[") + ] - transcript = self.model.transcribe(word_timestamps=True, audio=path_mp3) + transcript = self.model.transcribe(word_timestamps=True, audio=str(path_mp3)) - output_data = [] + lyrics_karaoke = [] segments = transcript["segments"] prev_n = 0 - for line in text_lines: + for line in lyrics_lines: last_word = line[-1] curr_n = len(line) curr_segments = segments[prev_n:curr_n] @@ -47,13 +46,15 @@ def get_line_timestamps( min_lev_value = 1000000 for segment in curr_segments: curr_word = segment["words"][0]["word"] - curr_end = segments["words"][0]["end"] + curr_end = segment["words"][0]["end"] curr_lev_value = self._levenshtein_distance(curr_word, last_word) if min_lev_value > curr_lev_value: min_lev_value = curr_lev_value min_lev_wordend = curr_end prev_n = curr_n - output_data.append({"line": line, "end_ts": min_lev_wordend}) + lyrics_karaoke.append({"line": line, "end_ts": min_lev_wordend}) - return output_data + # TODO: assert that lines are sorted by "end_ts" + print(lyrics_karaoke) + return lyrics_karaoke diff --git a/accompanist/collection/router.py b/accompanist/collection/router.py index faf687a..97520ff 100644 --- a/accompanist/collection/router.py +++ b/accompanist/collection/router.py @@ -56,6 +56,13 @@ async def update_track_lyrics(track_id: int): return track +# TODO: rename +@router.post("/tracks/{track_id}/lyrics_timestamps") +async def update_track_lyrics_timestamps(track_id: int): + track = await service.update_lyrics_timestamps(track_id) + return track + + @router.post("/update_lyrics_dev", include_in_schema=False) async def update_all_tracks_lyrics(): tracks = await TrackDAO.find_all() diff --git a/accompanist/collection/service.py b/accompanist/collection/service.py index e5e0424..16aa895 100644 --- a/accompanist/collection/service.py +++ b/accompanist/collection/service.py @@ -2,8 +2,10 @@ from accompanist.celery.tasks import process_album_task from accompanist.collection.dao import TrackDAO +from accompanist.collection.recognizer import LyricsTimestamper from accompanist.collection.schema import AlbumInfoFromUser, TrackUpdateRequest from accompanist.collection.service_genius import get_lyrics_from_genius +from accompanist.config import settings async def add_album(album_info: AlbumInfoFromUser): @@ -19,3 +21,14 @@ async def update_track_lyrics_by_id(track_id: int): update_request = TrackUpdateRequest(lyrics=lyrics, genius_url=genius_url) track = await TrackDAO.update(track.id, update_request) return track + + +# TODO: rename +async def update_lyrics_timestamps(track_id: int): + track = await TrackDAO.get_with_artist(track_id) + timestamper = LyricsTimestamper() + vocals_mp3_path = settings.STORAGE_PATH / track.filename_vocals + lyrics_karaoke = timestamper.get_karaoke_lyrics(vocals_mp3_path, track.lyrics) + update_request = TrackUpdateRequest(lyrics_karaoke=lyrics_karaoke) + track = await TrackDAO.update(track.id, update_request) + return track diff --git a/frontend/src/components/TrackComponent.vue b/frontend/src/components/TrackComponent.vue index 5c641c0..cc0703d 100644 --- a/frontend/src/components/TrackComponent.vue +++ b/frontend/src/components/TrackComponent.vue @@ -99,6 +99,18 @@ > Разметить караоке-текст +
+
+ +
+ +
=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9. extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"] test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"] +[[package]] +name = "numba" +version = "0.59.1" +description = "compiling Python code using LLVM" +category = "main" +optional = false +python-versions = ">=3.9" +files = [ + {file = "numba-0.59.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:97385a7f12212c4f4bc28f648720a92514bee79d7063e40ef66c2d30600fd18e"}, + {file = "numba-0.59.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0b77aecf52040de2a1eb1d7e314497b9e56fba17466c80b457b971a25bb1576d"}, + {file = "numba-0.59.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3476a4f641bfd58f35ead42f4dcaf5f132569c4647c6f1360ccf18ee4cda3990"}, + {file = "numba-0.59.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:525ef3f820931bdae95ee5379c670d5c97289c6520726bc6937a4a7d4230ba24"}, + {file = "numba-0.59.1-cp310-cp310-win_amd64.whl", hash = "sha256:990e395e44d192a12105eca3083b61307db7da10e093972ca285c85bef0963d6"}, + {file = "numba-0.59.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:43727e7ad20b3ec23ee4fc642f5b61845c71f75dd2825b3c234390c6d8d64051"}, + {file = "numba-0.59.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:411df625372c77959570050e861981e9d196cc1da9aa62c3d6a836b5cc338966"}, + {file = "numba-0.59.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2801003caa263d1e8497fb84829a7ecfb61738a95f62bc05693fcf1733e978e4"}, + {file = "numba-0.59.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:dd2842fac03be4e5324ebbbd4d2d0c8c0fc6e0df75c09477dd45b288a0777389"}, + {file = "numba-0.59.1-cp311-cp311-win_amd64.whl", hash = "sha256:0594b3dfb369fada1f8bb2e3045cd6c61a564c62e50cf1f86b4666bc721b3450"}, + {file = "numba-0.59.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:1cce206a3b92836cdf26ef39d3a3242fec25e07f020cc4feec4c4a865e340569"}, + {file = "numba-0.59.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8c8b4477763cb1fbd86a3be7050500229417bf60867c93e131fd2626edb02238"}, + {file = "numba-0.59.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7d80bce4ef7e65bf895c29e3889ca75a29ee01da80266a01d34815918e365835"}, + {file = "numba-0.59.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f7ad1d217773e89a9845886401eaaab0a156a90aa2f179fdc125261fd1105096"}, + {file = "numba-0.59.1-cp312-cp312-win_amd64.whl", hash = "sha256:5bf68f4d69dd3a9f26a9b23548fa23e3bcb9042e2935257b471d2a8d3c424b7f"}, + {file = "numba-0.59.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4e0318ae729de6e5dbe64c75ead1a95eb01fabfe0e2ebed81ebf0344d32db0ae"}, + {file = "numba-0.59.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0f68589740a8c38bb7dc1b938b55d1145244c8353078eea23895d4f82c8b9ec1"}, + {file = "numba-0.59.1-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:649913a3758891c77c32e2d2a3bcbedf4a69f5fea276d11f9119677c45a422e8"}, + {file = "numba-0.59.1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9712808e4545270291d76b9a264839ac878c5eb7d8b6e02c970dc0ac29bc8187"}, + {file = "numba-0.59.1-cp39-cp39-win_amd64.whl", hash = "sha256:8d51ccd7008a83105ad6a0082b6a2b70f1142dc7cfd76deb8c5a862367eb8c86"}, + {file = "numba-0.59.1.tar.gz", hash = "sha256:76f69132b96028d2774ed20415e8c528a34e3299a40581bae178f0994a2f370b"}, +] + +[package.dependencies] +llvmlite = ">=0.42.0dev0,<0.43" +numpy = ">=1.22,<1.27" + [[package]] name = "numpy" version = "1.26.4" @@ -1649,6 +1727,29 @@ files = [ antlr4-python3-runtime = ">=4.9.0,<4.10.0" PyYAML = ">=5.1.0" +[[package]] +name = "openai-whisper" +version = "20231117" +description = "Robust Speech Recognition via Large-Scale Weak Supervision" +category = "main" +optional = false +python-versions = ">=3.8" +files = [ + {file = "openai-whisper-20231117.tar.gz", hash = "sha256:7af424181436f1800cc0b7d75cf40ede34e9ddf1ba4983a910832fcf4aade4a4"}, +] + +[package.dependencies] +more-itertools = "*" +numba = "*" +numpy = "*" +tiktoken = "*" +torch = "*" +tqdm = "*" +triton = ">=2.0.0,<3" + +[package.extras] +dev = ["black", "flake8", "isort", "pytest", "scipy"] + [[package]] name = "openunmix" version = "1.2.1" @@ -2155,6 +2256,109 @@ files = [ {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"}, ] +[[package]] +name = "regex" +version = "2024.4.16" +description = "Alternative regular expression module, to replace re." +category = "main" +optional = false +python-versions = ">=3.7" +files = [ + {file = "regex-2024.4.16-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fb83cc090eac63c006871fd24db5e30a1f282faa46328572661c0a24a2323a08"}, + {file = "regex-2024.4.16-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c91e1763696c0eb66340c4df98623c2d4e77d0746b8f8f2bee2c6883fd1fe18"}, + {file = "regex-2024.4.16-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:10188fe732dec829c7acca7422cdd1bf57d853c7199d5a9e96bb4d40db239c73"}, + {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:956b58d692f235cfbf5b4f3abd6d99bf102f161ccfe20d2fd0904f51c72c4c66"}, + {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a70b51f55fd954d1f194271695821dd62054d949efd6368d8be64edd37f55c86"}, + {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c02fcd2bf45162280613d2e4a1ca3ac558ff921ae4e308ecb307650d3a6ee51"}, + {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c4ed75ea6892a56896d78f11006161eea52c45a14994794bcfa1654430984b22"}, + {file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd727ad276bb91928879f3aa6396c9a1d34e5e180dce40578421a691eeb77f47"}, + {file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7cbc5d9e8a1781e7be17da67b92580d6ce4dcef5819c1b1b89f49d9678cc278c"}, + {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:78fddb22b9ef810b63ef341c9fcf6455232d97cfe03938cbc29e2672c436670e"}, + {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:445ca8d3c5a01309633a0c9db57150312a181146315693273e35d936472df912"}, + {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:95399831a206211d6bc40224af1c635cb8790ddd5c7493e0bd03b85711076a53"}, + {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:7731728b6568fc286d86745f27f07266de49603a6fdc4d19c87e8c247be452af"}, + {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4facc913e10bdba42ec0aee76d029aedda628161a7ce4116b16680a0413f658a"}, + {file = "regex-2024.4.16-cp310-cp310-win32.whl", hash = "sha256:911742856ce98d879acbea33fcc03c1d8dc1106234c5e7d068932c945db209c0"}, + {file = "regex-2024.4.16-cp310-cp310-win_amd64.whl", hash = "sha256:e0a2df336d1135a0b3a67f3bbf78a75f69562c1199ed9935372b82215cddd6e2"}, + {file = "regex-2024.4.16-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1210365faba7c2150451eb78ec5687871c796b0f1fa701bfd2a4a25420482d26"}, + {file = "regex-2024.4.16-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9ab40412f8cd6f615bfedea40c8bf0407d41bf83b96f6fc9ff34976d6b7037fd"}, + {file = "regex-2024.4.16-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:fd80d1280d473500d8086d104962a82d77bfbf2b118053824b7be28cd5a79ea5"}, + {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bb966fdd9217e53abf824f437a5a2d643a38d4fd5fd0ca711b9da683d452969"}, + {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:20b7a68444f536365af42a75ccecb7ab41a896a04acf58432db9e206f4e525d6"}, + {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b74586dd0b039c62416034f811d7ee62810174bb70dffcca6439f5236249eb09"}, + {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c8290b44d8b0af4e77048646c10c6e3aa583c1ca67f3b5ffb6e06cf0c6f0f89"}, + {file = "regex-2024.4.16-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2d80a6749724b37853ece57988b39c4e79d2b5fe2869a86e8aeae3bbeef9eb0"}, + {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:3a1018e97aeb24e4f939afcd88211ace472ba566efc5bdf53fd8fd7f41fa7170"}, + {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8d015604ee6204e76569d2f44e5a210728fa917115bef0d102f4107e622b08d5"}, + {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:3d5ac5234fb5053850d79dd8eb1015cb0d7d9ed951fa37aa9e6249a19aa4f336"}, + {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:0a38d151e2cdd66d16dab550c22f9521ba79761423b87c01dae0a6e9add79c0d"}, + {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:159dc4e59a159cb8e4e8f8961eb1fa5d58f93cb1acd1701d8aff38d45e1a84a6"}, + {file = "regex-2024.4.16-cp311-cp311-win32.whl", hash = "sha256:ba2336d6548dee3117520545cfe44dc28a250aa091f8281d28804aa8d707d93d"}, + {file = "regex-2024.4.16-cp311-cp311-win_amd64.whl", hash = "sha256:8f83b6fd3dc3ba94d2b22717f9c8b8512354fd95221ac661784df2769ea9bba9"}, + {file = "regex-2024.4.16-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:80b696e8972b81edf0af2a259e1b2a4a661f818fae22e5fa4fa1a995fb4a40fd"}, + {file = "regex-2024.4.16-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d61ae114d2a2311f61d90c2ef1358518e8f05eafda76eaf9c772a077e0b465ec"}, + {file = "regex-2024.4.16-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8ba6745440b9a27336443b0c285d705ce73adb9ec90e2f2004c64d95ab5a7598"}, + {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6295004b2dd37b0835ea5c14a33e00e8cfa3c4add4d587b77287825f3418d310"}, + {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4aba818dcc7263852aabb172ec27b71d2abca02a593b95fa79351b2774eb1d2b"}, + {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0800631e565c47520aaa04ae38b96abc5196fe8b4aa9bd864445bd2b5848a7a"}, + {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08dea89f859c3df48a440dbdcd7b7155bc675f2fa2ec8c521d02dc69e877db70"}, + {file = "regex-2024.4.16-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eeaa0b5328b785abc344acc6241cffde50dc394a0644a968add75fcefe15b9d4"}, + {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:4e819a806420bc010489f4e741b3036071aba209f2e0989d4750b08b12a9343f"}, + {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:c2d0e7cbb6341e830adcbfa2479fdeebbfbb328f11edd6b5675674e7a1e37730"}, + {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:91797b98f5e34b6a49f54be33f72e2fb658018ae532be2f79f7c63b4ae225145"}, + {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:d2da13568eff02b30fd54fccd1e042a70fe920d816616fda4bf54ec705668d81"}, + {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:370c68dc5570b394cbaadff50e64d705f64debed30573e5c313c360689b6aadc"}, + {file = "regex-2024.4.16-cp312-cp312-win32.whl", hash = "sha256:904c883cf10a975b02ab3478bce652f0f5346a2c28d0a8521d97bb23c323cc8b"}, + {file = "regex-2024.4.16-cp312-cp312-win_amd64.whl", hash = "sha256:785c071c982dce54d44ea0b79cd6dfafddeccdd98cfa5f7b86ef69b381b457d9"}, + {file = "regex-2024.4.16-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e2f142b45c6fed48166faeb4303b4b58c9fcd827da63f4cf0a123c3480ae11fb"}, + {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e87ab229332ceb127a165612d839ab87795972102cb9830e5f12b8c9a5c1b508"}, + {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81500ed5af2090b4a9157a59dbc89873a25c33db1bb9a8cf123837dcc9765047"}, + {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b340cccad138ecb363324aa26893963dcabb02bb25e440ebdf42e30963f1a4e0"}, + {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c72608e70f053643437bd2be0608f7f1c46d4022e4104d76826f0839199347a"}, + {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a01fe2305e6232ef3e8f40bfc0f0f3a04def9aab514910fa4203bafbc0bb4682"}, + {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:03576e3a423d19dda13e55598f0fd507b5d660d42c51b02df4e0d97824fdcae3"}, + {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:549c3584993772e25f02d0656ac48abdda73169fe347263948cf2b1cead622f3"}, + {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:34422d5a69a60b7e9a07a690094e824b66f5ddc662a5fc600d65b7c174a05f04"}, + {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:5f580c651a72b75c39e311343fe6875d6f58cf51c471a97f15a938d9fe4e0d37"}, + {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:3399dd8a7495bbb2bacd59b84840eef9057826c664472e86c91d675d007137f5"}, + {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8d1f86f3f4e2388aa3310b50694ac44daefbd1681def26b4519bd050a398dc5a"}, + {file = "regex-2024.4.16-cp37-cp37m-win32.whl", hash = "sha256:dd5acc0a7d38fdc7a3a6fd3ad14c880819008ecb3379626e56b163165162cc46"}, + {file = "regex-2024.4.16-cp37-cp37m-win_amd64.whl", hash = "sha256:ba8122e3bb94ecda29a8de4cf889f600171424ea586847aa92c334772d200331"}, + {file = "regex-2024.4.16-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:743deffdf3b3481da32e8a96887e2aa945ec6685af1cfe2bcc292638c9ba2f48"}, + {file = "regex-2024.4.16-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7571f19f4a3fd00af9341c7801d1ad1967fc9c3f5e62402683047e7166b9f2b4"}, + {file = "regex-2024.4.16-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:df79012ebf6f4efb8d307b1328226aef24ca446b3ff8d0e30202d7ebcb977a8c"}, + {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e757d475953269fbf4b441207bb7dbdd1c43180711b6208e129b637792ac0b93"}, + {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4313ab9bf6a81206c8ac28fdfcddc0435299dc88cad12cc6305fd0e78b81f9e4"}, + {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d83c2bc678453646f1a18f8db1e927a2d3f4935031b9ad8a76e56760461105dd"}, + {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9df1bfef97db938469ef0a7354b2d591a2d438bc497b2c489471bec0e6baf7c4"}, + {file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62120ed0de69b3649cc68e2965376048793f466c5a6c4370fb27c16c1beac22d"}, + {file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c2ef6f7990b6e8758fe48ad08f7e2f66c8f11dc66e24093304b87cae9037bb4a"}, + {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8fc6976a3395fe4d1fbeb984adaa8ec652a1e12f36b56ec8c236e5117b585427"}, + {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:03e68f44340528111067cecf12721c3df4811c67268b897fbe695c95f860ac42"}, + {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ec7e0043b91115f427998febaa2beb82c82df708168b35ece3accb610b91fac1"}, + {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:c21fc21a4c7480479d12fd8e679b699f744f76bb05f53a1d14182b31f55aac76"}, + {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:12f6a3f2f58bb7344751919a1876ee1b976fe08b9ffccb4bbea66f26af6017b9"}, + {file = "regex-2024.4.16-cp38-cp38-win32.whl", hash = "sha256:479595a4fbe9ed8f8f72c59717e8cf222da2e4c07b6ae5b65411e6302af9708e"}, + {file = "regex-2024.4.16-cp38-cp38-win_amd64.whl", hash = "sha256:0534b034fba6101611968fae8e856c1698da97ce2efb5c2b895fc8b9e23a5834"}, + {file = "regex-2024.4.16-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:a7ccdd1c4a3472a7533b0a7aa9ee34c9a2bef859ba86deec07aff2ad7e0c3b94"}, + {file = "regex-2024.4.16-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6f2f017c5be19984fbbf55f8af6caba25e62c71293213f044da3ada7091a4455"}, + {file = "regex-2024.4.16-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:803b8905b52de78b173d3c1e83df0efb929621e7b7c5766c0843704d5332682f"}, + {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:684008ec44ad275832a5a152f6e764bbe1914bea10968017b6feaecdad5736e0"}, + {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65436dce9fdc0aeeb0a0effe0839cb3d6a05f45aa45a4d9f9c60989beca78b9c"}, + {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ea355eb43b11764cf799dda62c658c4d2fdb16af41f59bb1ccfec517b60bcb07"}, + {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98c1165f3809ce7774f05cb74e5408cd3aa93ee8573ae959a97a53db3ca3180d"}, + {file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cccc79a9be9b64c881f18305a7c715ba199e471a3973faeb7ba84172abb3f317"}, + {file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:00169caa125f35d1bca6045d65a662af0202704489fada95346cfa092ec23f39"}, + {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6cc38067209354e16c5609b66285af17a2863a47585bcf75285cab33d4c3b8df"}, + {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:23cff1b267038501b179ccbbd74a821ac4a7192a1852d1d558e562b507d46013"}, + {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:b9d320b3bf82a39f248769fc7f188e00f93526cc0fe739cfa197868633d44701"}, + {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:89ec7f2c08937421bbbb8b48c54096fa4f88347946d4747021ad85f1b3021b3c"}, + {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4918fd5f8b43aa7ec031e0fef1ee02deb80b6afd49c85f0790be1dc4ce34cb50"}, + {file = "regex-2024.4.16-cp39-cp39-win32.whl", hash = "sha256:684e52023aec43bdf0250e843e1fdd6febbe831bd9d52da72333fa201aaa2335"}, + {file = "regex-2024.4.16-cp39-cp39-win_amd64.whl", hash = "sha256:e697e1c0238133589e00c244a8b676bc2cfc3ab4961318d902040d099fec7483"}, + {file = "regex-2024.4.16.tar.gz", hash = "sha256:fa454d26f2e87ad661c4f0c5a5fe4cf6aab1e307d1b94f16ffdfcb089ba685c0"}, +] + [[package]] name = "requests" version = "2.31.0" @@ -2417,6 +2621,59 @@ files = [ [package.dependencies] mpmath = ">=0.19" +[[package]] +name = "tiktoken" +version = "0.6.0" +description = "tiktoken is a fast BPE tokeniser for use with OpenAI's models" +category = "main" +optional = false +python-versions = ">=3.8" +files = [ + {file = "tiktoken-0.6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:277de84ccd8fa12730a6b4067456e5cf72fef6300bea61d506c09e45658d41ac"}, + {file = "tiktoken-0.6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9c44433f658064463650d61387623735641dcc4b6c999ca30bc0f8ba3fccaf5c"}, + {file = "tiktoken-0.6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afb9a2a866ae6eef1995ab656744287a5ac95acc7e0491c33fad54d053288ad3"}, + {file = "tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c62c05b3109fefca26fedb2820452a050074ad8e5ad9803f4652977778177d9f"}, + {file = "tiktoken-0.6.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0ef917fad0bccda07bfbad835525bbed5f3ab97a8a3e66526e48cdc3e7beacf7"}, + {file = "tiktoken-0.6.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e095131ab6092d0769a2fda85aa260c7c383072daec599ba9d8b149d2a3f4d8b"}, + {file = "tiktoken-0.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:05b344c61779f815038292a19a0c6eb7098b63c8f865ff205abb9ea1b656030e"}, + {file = "tiktoken-0.6.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cefb9870fb55dca9e450e54dbf61f904aab9180ff6fe568b61f4db9564e78871"}, + {file = "tiktoken-0.6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:702950d33d8cabc039845674107d2e6dcabbbb0990ef350f640661368df481bb"}, + {file = "tiktoken-0.6.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8d49d076058f23254f2aff9af603863c5c5f9ab095bc896bceed04f8f0b013a"}, + {file = "tiktoken-0.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:430bc4e650a2d23a789dc2cdca3b9e5e7eb3cd3935168d97d43518cbb1f9a911"}, + {file = "tiktoken-0.6.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:293cb8669757301a3019a12d6770bd55bec38a4d3ee9978ddbe599d68976aca7"}, + {file = "tiktoken-0.6.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:7bd1a288b7903aadc054b0e16ea78e3171f70b670e7372432298c686ebf9dd47"}, + {file = "tiktoken-0.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:ac76e000183e3b749634968a45c7169b351e99936ef46f0d2353cd0d46c3118d"}, + {file = "tiktoken-0.6.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:17cc8a4a3245ab7d935c83a2db6bb71619099d7284b884f4b2aea4c74f2f83e3"}, + {file = "tiktoken-0.6.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:284aebcccffe1bba0d6571651317df6a5b376ff6cfed5aeb800c55df44c78177"}, + {file = "tiktoken-0.6.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0c1a3a5d33846f8cd9dd3b7897c1d45722f48625a587f8e6f3d3e85080559be8"}, + {file = "tiktoken-0.6.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6318b2bb2337f38ee954fd5efa82632c6e5ced1d52a671370fa4b2eff1355e91"}, + {file = "tiktoken-0.6.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:1f5f0f2ed67ba16373f9a6013b68da298096b27cd4e1cf276d2d3868b5c7efd1"}, + {file = "tiktoken-0.6.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:75af4c0b16609c2ad02581f3cdcd1fb698c7565091370bf6c0cf8624ffaba6dc"}, + {file = "tiktoken-0.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:45577faf9a9d383b8fd683e313cf6df88b6076c034f0a16da243bb1c139340c3"}, + {file = "tiktoken-0.6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7c1492ab90c21ca4d11cef3a236ee31a3e279bb21b3fc5b0e2210588c4209e68"}, + {file = "tiktoken-0.6.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e2b380c5b7751272015400b26144a2bab4066ebb8daae9c3cd2a92c3b508fe5a"}, + {file = "tiktoken-0.6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c9f497598b9f58c99cbc0eb764b4a92272c14d5203fc713dd650b896a03a50ad"}, + {file = "tiktoken-0.6.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e65e8bd6f3f279d80f1e1fbd5f588f036b9a5fa27690b7f0cc07021f1dfa0839"}, + {file = "tiktoken-0.6.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5f1495450a54e564d236769d25bfefbf77727e232d7a8a378f97acddee08c1ae"}, + {file = "tiktoken-0.6.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6c4e4857d99f6fb4670e928250835b21b68c59250520a1941618b5b4194e20c3"}, + {file = "tiktoken-0.6.0-cp38-cp38-win_amd64.whl", hash = "sha256:168d718f07a39b013032741867e789971346df8e89983fe3c0ef3fbd5a0b1cb9"}, + {file = "tiktoken-0.6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:47fdcfe11bd55376785a6aea8ad1db967db7f66ea81aed5c43fad497521819a4"}, + {file = "tiktoken-0.6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fb7d2ccbf1a7784810aff6b80b4012fb42c6fc37eaa68cb3b553801a5cc2d1fc"}, + {file = "tiktoken-0.6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1ccb7a111ee76af5d876a729a347f8747d5ad548e1487eeea90eaf58894b3138"}, + {file = "tiktoken-0.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2048e1086b48e3c8c6e2ceeac866561374cd57a84622fa49a6b245ffecb7744"}, + {file = "tiktoken-0.6.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:07f229a5eb250b6403a61200199cecf0aac4aa23c3ecc1c11c1ca002cbb8f159"}, + {file = "tiktoken-0.6.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:432aa3be8436177b0db5a2b3e7cc28fd6c693f783b2f8722539ba16a867d0c6a"}, + {file = "tiktoken-0.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:8bfe8a19c8b5c40d121ee7938cd9c6a278e5b97dc035fd61714b4f0399d2f7a1"}, + {file = "tiktoken-0.6.0.tar.gz", hash = "sha256:ace62a4ede83c75b0374a2ddfa4b76903cf483e9cb06247f566be3bf14e6beed"}, +] + +[package.dependencies] +regex = ">=2022.1.18" +requests = ">=2.26.0" + +[package.extras] +blobfile = ["blobfile (>=2)"] + [[package]] name = "tomli" version = "2.0.1" @@ -3066,4 +3323,4 @@ requests = ">=2.22" [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "4739b24ef517a1c99cddafa5dae84b9af2338bacc4558d54777949a0717cd674" +content-hash = "a61e06a5bb0b7d728297ce89580ee9129402f185c40ffe13411fd7959a267800" diff --git a/pyproject.toml b/pyproject.toml index 429dedb..cc6639a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -24,6 +24,7 @@ sqladmin = "^0.16.1" pytest = "^8.1.1" pytest-asyncio = "^0.23.6" httpx = "^0.27.0" +openai-whisper = "^20231117" [tool.poetry.group.dev.dependencies] ruff = "^0.3.2"