Buckets:
| { | |
| "audio_v2": { | |
| "files": 35629, | |
| "bytes_total": 1211145391272, | |
| "ext_bytes": { | |
| "m4a": 877257571660, | |
| "mp3": 333800068261, | |
| "xml": 59432132, | |
| "vtt": 20019255, | |
| "json": 4318893, | |
| "json3": 989806, | |
| "ttml": 847034, | |
| "srv1": 735719 | |
| }, | |
| "ext_count": { | |
| "m4a": 29059, | |
| "mp3": 5820, | |
| "vtt": 599, | |
| "xml": 80, | |
| "json3": 13, | |
| "srv1": 13, | |
| "srv2": 13, | |
| "srv3": 13 | |
| } | |
| }, | |
| "crowd-transcribe-v5": { | |
| "files": 48, | |
| "sample_rows": "[{\"uuid\": \"SmallBigHistory/2021.08.25 \u05e1\u05e4\u05d9\u05d9\u05e9\u05dc \u05d7\u05d9\u05e8\u05d5\u05dd! - \u05d0\u05e4\u05d2\u05e0\u05d9\u05e1\u05d8\u05df, \u05d4\u05d8\u05dc\u05d9\u05d1\u05d0\u05df \u05d5\u05d0\u05dc\u05db\u05e1 \u05d2\u05e8\u05d9\u05e0\u05d1\u05e8\u05d2/298\", \"audio\": {\"bytes\": \"b'ID3\\\\x04\\\\x00\\\\x00\\\\x00\\\\x00\\\\x01|TPE1\\\\x00\\\\x00\\\\x00\\\\x18\\\\x00\\\\x00\\\\x03Historia Gdola Baktana\\\\x00TIT2\\\\x00\\\\x00\\\\x006\\\\x00\\\\x00\\\\x03AFGHANISTAN SPECIAL - Alex Greenberg and the Taliban\\\\x00TXXX\\\\x00\\\\x00\\\\x00X\\\\x00\\\\x00\\\\x03comment\\\\x00Intro and outro: \\\"Corporate Innovative\\\" by Scott Holmes @ scottholmesmusic.com\\\\x00TXXX\\\\x00\\\\x00\\\\x00\\\\x0b\\\\x00\\\\x00\\\\x03Software\\\\x00\\\\x00TSSE\\\\x00\\\\x00\\\\x00\\\\x0f\\\\x00\\\\x00\\\\x03Lavf58.45.100\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\xff\\\\xfb\\\\x88\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00Xing\\\\x00\\\\x00\\\\x00\\\\x0f\\\\x00\\\\x00\\\\x00u\\\\x00\\\\x00\\\\xdd\\\\x10\\\\x00\\\\x07\\\\n\\\\r\\\\x0f\\\\x12\\\\x16\\\\x18\\\\x1a\\\\x1c\\\\x1e $&(*+-1478;=@ADFHJPTVXZ]acdehjoqsvx{\\\\x80\\\\x83\\\\x85\\\\x86\\\\x89\\\\x8e\\\\x8f\\\\x91\\\\x93\\\\x96\\\\x98\\\\x9c\\\\x9e\\\\xa0\\\\xa2\\\\xa4\\\\xa6\\\\xaa\\\\xac\\\\xaf\\\\xb2\\\\xb4\\\\xb6\\\\xb9\\\\xbb\\\\xbd\\\\xbf\\\\xc1\\\\xc4\\\\xc9\\\\xcb\\\\xcd\\\\xcf\\\\xd1\\\\xd3\\\\xd6\\\\xd8\\\\xdc\\\\xdf\\\\xe2\\\\xe3\\\\xe8\\\\xeb\\\\xed\\\\xef\\\\xf1\\\\xf2\\\\xf7\\\\xf9\\\\xfb\\\\xfd\\\\xfe\\\\x00\\\\x00\\\\x00\\\\x00LAME3.100\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\xdd\\\\x10\\\\xa5\\\\x01\\\\xa8\\\\xc4\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\", | |
| "rows_sampled_from": 6, | |
| "schema": [ | |
| "uuid", | |
| "audio", | |
| "orig_sentence", | |
| "sentence", | |
| "is_retranscribe", | |
| "transcriber", | |
| "extra_data" | |
| ], | |
| "rows_est_full": 165688 | |
| }, | |
| "audio-labeled": { | |
| "files": 23, | |
| "sample_rows": "[{\"uuid\": \"Mindset/2020.08.04 \u05dc\u05de\u05d9\u05d3\u05d4 \u05de\u05ea\u05de\u05d3\u05ea \u05d5\u05de\u05d9\u05d5\u05de\u05e0\u05d5\u05d9\u05d5\u05ea \u05d4\u05e2\u05ea\u05d9\u05d3 \u05d1\u05d0\u05e8\u05d2\u05d5\u05e0\u05d9\u05dd - \u05e8\u05d9\u05e0\u05ea\u05d9\u05d4 \u05d1\u05e8\u05d5\u05db\u05d9\u05dd \u05dc\u05d5\u05d9\u05df - \u05e4\u05e8\u05e7 48/476\", \"audio\": {\"bytes\": \"b'ID3\\\\x04\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00#TSSE\\\\x00\\\\x00\\\\x00\\\\x0f\\\\x00\\\\x00\\\\x03Lavf58.45.100\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\xff\\\\xfb\\\\xe0\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00Info\\\\x00\\\\x00\\\\x00\\\\x0f\\\\x00\\\\x00\\\\x00\\\\x9a\\\\x00\\\\x02x\\\\xa6\\\\x00\\\\x04\\\\x08\\\\t\\\\r\\\\x0e\\\\x12\\\\x13\\\\x17\\\\x18\\\\x1c\\\\x1d!$%)*./3489=>BEGJKOPTUYZ^_cfhkmpquvz{\\\\x7f\\\\x82\\\\x84\\\\x87\\\\x89\\\\x8c\\\\x8e\\\\x91\\\\x92\\\\x96\\\\x97\\\\x9b\\\\x9c\\\\xa0\\\\xa3\\\\xa5\\\\xa8\\\\xaa\\\\xad\\\\xaf\\\\xb2\\\\xb4\\\\xb7\\\\xb8\\\\xbc\\\\xbd\\\\xc1\\\\xc4\\\\xc6\\\\xc9\\\\xcb\\\\xce\\\\xd0\\\\xd3\\\\xd5\\\\xd8\\\\xda\\\\xdd\\\\xde\\\\xe2\\\\xe5\\\\xe7\\\\xea\\\\xec\\\\xef\\\\xf1\\\\xf4\\\\xf6\\\\xf9\\\\xfb\\\\xfe\\\\x00\\\\x00\\\\x00\\\\x00LAME3.97 \\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\"\\\\x0b\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x02x\\\\xa6\\\\x85\\\\x90\\\\xdbS\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\x00\\\\", | |
| "rows_sampled_from": 6, | |
| "schema": [ | |
| "uuid", | |
| "audio", | |
| "orig_text", | |
| "text", | |
| "stats" | |
| ], | |
| "rows_est_full": 86978 | |
| }, | |
| "audio-vad": { | |
| "files": 1591, | |
| "errors": [ | |
| "data/data-00000-of-00181.arrow: Parquet magic bytes not found in footer. Either the file is corrupted or this is not a parquet file.", | |
| "data/data-00001-of-00181.arrow: Parquet magic bytes not found in footer. Either the file is corrupted or this is not a parquet file.", | |
| "data/data-00002-of-00181.arrow: Parquet magic bytes not found in footer. Either the file is corrupted or this is not a parquet file.", | |
| "data/data-00003-of-00181.arrow: Parquet magic bytes not found in footer. Either the file is corrupted or this is not a parquet file.", | |
| "data/data-00004-of-00181.arrow: Parquet magic bytes not found in footer. Either the file is corrupted or this is not a parquet file.", | |
| "data/data-00005-of-00181.arrow: Parquet magic bytes not found in footer. Either the file is corrupted or this is not a parquet file." | |
| ], | |
| "rows_sampled_from": 0, | |
| "schema": null, | |
| "rows_est_full": 0 | |
| }, | |
| "audio-transcripts": { | |
| "files": 5, | |
| "errors": [ | |
| "data/data-00000-of-00002.arrow: 403 Client Error. (Request ID: Root=1-6acb3a24-390a0d423c3053d258ed50ae;cd251497-6bac-4e06-88b4-b192335c5262)\n\nCannot access gated repo for url https://huggingface.co/datasets/ivrit-ai/audio-transcripts/resolve/main/data/data-00000-of-00002.arrow.\nAccess to dataset ivrit-ai/audio-transcripts is restricted and you are not in the authorized list. Visit https://huggingface.co/datasets/ivrit-ai/audio-transcripts to ask for access.", | |
| "data/data-00001-of-00002.arrow: 403 Client Error. (Request ID: Root=1-6acb3a24-1522c4cb0bbd6f115579a1b6;8bccc774-2896-4b83-ad96-2f2920df5015)\n\nCannot access gated repo for url https://huggingface.co/datasets/ivrit-ai/audio-transcripts/resolve/main/data/data-00001-of-00002.arrow.\nAccess to dataset ivrit-ai/audio-transcripts is restricted and you are not in the authorized list. Visit https://huggingface.co/datasets/ivrit-ai/audio-transcripts to ask for access.", | |
| "data/train-00000-of-00003.parquet: 403 Client Error. (Request ID: Root=1-6acb3a24-784bd6d663bad8d80169f6d1;64e64050-5389-4ada-a87b-62f9d1f3645a)\n\nCannot access gated repo for url https://huggingface.co/datasets/ivrit-ai/audio-transcripts/resolve/main/data/train-00000-of-00003.parquet.\nAccess to dataset ivrit-ai/audio-transcripts is restricted and you are not in the authorized list. Visit https://huggingface.co/datasets/ivrit-ai/audio-transcripts to ask for access.", | |
| "data/train-00001-of-00003.parquet: 403 Client Error. (Request ID: Root=1-6acb3a24-4b9e79dc732b501b18d508be;f7f4e9c8-3419-4069-9424-fb90b4c5441a)\n\nCannot access gated repo for url https://huggingface.co/datasets/ivrit-ai/audio-transcripts/resolve/main/data/train-00001-of-00003.parquet.\nAccess to dataset ivrit-ai/audio-transcripts is restricted and you are not in the authorized list. Visit https://huggingface.co/datasets/ivrit-ai/audio-transcripts to ask for access.", | |
| "data/train-00002-of-00003.parquet: 403 Client Error. (Request ID: Root=1-6acb3a24-4e21fffc77d7291f14928bf0;74a357f4-3561-46dc-b0f7-939d35f7f6d5)\n\nCannot access gated repo for url https://huggingface.co/datasets/ivrit-ai/audio-transcripts/resolve/main/data/train-00002-of-00003.parquet.\nAccess to dataset ivrit-ai/audio-transcripts is restricted and you are not in the authorized list. Visit https://huggingface.co/datasets/ivrit-ai/audio-transcripts to ask for access." | |
| ], | |
| "rows_sampled_from": 0, | |
| "schema": null, | |
| "rows_est_full": 0 | |
| } | |
| } |
Xet Storage Details
- Size:
- 10.1 kB
- Xet hash:
- 46e3fa0e76791e3eb8914d0b3e175615ff40b9eb8b568ccbd318804383426631
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.