[{"_id":"6735ea1db403886c21f155f0","id":"SPRINGLab/IndicTTS-English","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-14T13:27:33.000Z","likes":3,"trendingScore":1,"private":false,"sha":"db1813df187a7265ea91c5506941054622a45dc3","downloads":663,"tags":["size_categories:100K<n<1M","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-14T12:16:29.000Z","key":""},{"_id":"66460d54f9d985c05b348753","id":"SPRINGLab/BPCC_cleaned","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-12T12:23:19.000Z","likes":1,"trendingScore":0,"private":false,"sha":"a4d50cc8da5c950a9fb41071f7f9d8b641050c90","description":"A curated subset of Bharat Parallel Corpus Collection (BPCC) for 8 Indian languages. \nTranslation pairs are filtered with LABSE score(>0.9) and further preprocessed.\nUseful for training high-quality translation models.\n","downloads":85,"tags":["task_categories:translation","language:bn","language:hi","language:ta","language:te","language:mr","language:ml","language:kn","language:gu","size_categories:1M<n<10M","format:parquet","modality:text","library:datasets","library:pandas","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-05-16T13:42:44.000Z","key":""},{"_id":"66c4f85ee8f01fe34e88dbc4","id":"SPRINGLab/shiksha","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-12-16T09:54:30.000Z","likes":1,"trendingScore":0,"private":false,"sha":"b0d6eb9e6eda506c51be86c05f0a12fce24e1ff5","description":"\n\t\n\t\t\n\t\tShiksha Dataset\n\t\n\nThis is a Technical Domain focused Translation Dataset for 8 Indian Languages. It consists of more than 2.5 million rows of translation pairs between all 8 languages and English.\nThis data has been derived from raw NPTEL documents. More information on this can be found in our paper: https://arxiv.org/abs/2412.09025\nIf you use this data in your work, please cite us:\n@misc{joglekar2024shikshatechnicaldomainfocused,\n      title={Shiksha: A Technical Domain focused… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/shiksha.","downloads":52,"tags":["task_categories:translation","language:hi","language:bn","language:ta","language:te","language:kn","language:gu","language:mr","language:ml","license:cc-by-4.0","size_categories:1M<n<10M","format:parquet","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","arxiv:2412.09025","region:us"],"createdAt":"2024-08-20T20:11:10.000Z","key":""},{"_id":"66ec014f4daaea1273dd6e6b","id":"SPRINGLab/asr-task-data","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-09-20T10:02:36.000Z","likes":1,"trendingScore":0,"private":false,"sha":"c8c1a65307284e0ef3c06725cb4b31259dcbc915","downloads":30,"tags":["size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-09-19T10:47:43.000Z","key":""},{"_id":"6720b4ae65356de1c1ec2338","id":"SPRINGLab/Hindi-1482Hrs","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-10-29T13:03:00.000Z","likes":5,"trendingScore":0,"private":false,"sha":"ff425d37df67f371dbd3da968f82d7d8028572a3","downloads":443,"tags":["size_categories:100K<n<1M","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-10-29T10:10:54.000Z","key":""},{"_id":"6729ecbb83c26a0c22c4b222","id":"SPRINGLab/IndicTTS-Hindi","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-05T10:14:34.000Z","likes":36,"trendingScore":0,"private":false,"sha":"e8de3acc27c78c97a4360a51a4f13bc6db354543","description":"\n\t\n\t\t\n\t\tHindi Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Hindi monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Hindi\nTotal Duration: ~10.33 hours (Male: 5.16 hours, Female: 5.18 hours)\nAudio Format: WAV\nSampling Rate: 48000Hz… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS-Hindi.","downloads":976,"tags":["task_categories:text-to-speech","language:hi","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-05T10:00:27.000Z","key":""},{"_id":"672b09e0dba831894fe15869","id":"SPRINGLab/IndicVoices-R_Hindi","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-06T08:03:15.000Z","likes":11,"trendingScore":0,"private":false,"sha":"8f9913669e3505acd38b97fa38bd027f49afeeef","downloads":370,"tags":["task_categories:text-to-speech","language:hi","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-06T06:17:04.000Z","key":""},{"_id":"6731d618b84a82862f8f2678","id":"SPRINGLab/SPRING_INX_Assamese_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-22T11:33:56.000Z","likes":0,"trendingScore":0,"private":false,"sha":"996bfa4853d1d392254e61d0ac900f5e3f2f8465","downloads":187,"tags":["language:as","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-11T10:02:00.000Z","key":""},{"_id":"6734a3cbc74a3af1aefd8aa4","id":"SPRINGLab/SPRING_INX_Tamil_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-14T10:03:28.000Z","likes":1,"trendingScore":0,"private":false,"sha":"3931b31eaa37449c263d380fd215b18c36558846","downloads":161,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-13T13:04:11.000Z","key":""},{"_id":"6735c68903e3b0052162153c","id":"SPRINGLab/SPRING_INX_Tamil_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-14T09:57:10.000Z","likes":0,"trendingScore":0,"private":false,"sha":"5cdae7158e86e3124a309d0fbb6d591b2691873e","downloads":200,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-14T09:44:41.000Z","key":""},{"_id":"6735cd75e90a2e0b0dbf462e","id":"SPRINGLab/SPRING_INX_Assamese_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-14T10:18:15.000Z","likes":0,"trendingScore":0,"private":false,"sha":"77cede1272968e14bd110ae26b7e5add3445903f","downloads":24,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-14T10:14:13.000Z","key":""},{"_id":"6735e019049bfa3a90586804","id":"SPRINGLab/SPRING_INX_Bengali_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-14T12:09:54.000Z","likes":0,"trendingScore":0,"private":false,"sha":"84a3fb13194b7646ec2a3071bf7e83840461acbc","downloads":299,"tags":["size_categories:100K<n<1M","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-14T11:33:45.000Z","key":""},{"_id":"6735f03555a98f9a6e768e65","id":"SPRINGLab/SPRING_INX_Bengali_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-14T13:11:47.000Z","likes":1,"trendingScore":0,"private":false,"sha":"794a895662bb9b6235ab29345a3515005207660a","downloads":307,"tags":["size_categories:100K<n<1M","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-14T12:42:29.000Z","key":""},{"_id":"6736df7208a190b1ca455966","id":"SPRINGLab/SPRING_INX_Gujarati_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-15T06:00:06.000Z","likes":0,"trendingScore":0,"private":false,"sha":"6cbbaf73ba99c7afbc78fd589e2cebda74959746","downloads":103,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-15T05:43:14.000Z","key":""},{"_id":"6736e68f6dec98c400b21412","id":"SPRINGLab/SPRING_INX_Gujarati_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-15T06:19:35.000Z","likes":0,"trendingScore":0,"private":false,"sha":"c17325ec48cfa78221f8127d62e3ce8f988bbd97","downloads":180,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-15T06:13:35.000Z","key":""},{"_id":"6736f16195032043a4c69136","id":"SPRINGLab/SPRING_INX_Kannada_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-15T07:08:01.000Z","likes":0,"trendingScore":0,"private":false,"sha":"bd9e8f130d19353ebee691fddf34ac5f99143416","downloads":69,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-15T06:59:45.000Z","key":""},{"_id":"6736f7bbe11b21bf778a398c","id":"SPRINGLab/SPRING_INX_Malayalam_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-15T07:47:18.000Z","likes":0,"trendingScore":0,"private":false,"sha":"0843a854a60a1264bf42b1a869ddc85890f19bb1","downloads":393,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-15T07:26:51.000Z","key":""},{"_id":"67372521b42b389127514f9a","id":"SPRINGLab/SPRING_INX_Malayalam_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-15T10:47:41.000Z","likes":0,"trendingScore":0,"private":false,"sha":"d74480400f3d98af82ddc7657d30c93920b1035b","downloads":86,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-15T10:40:33.000Z","key":""},{"_id":"6738747d1c219779aa298f8d","id":"SPRINGLab/SPRING_INX_Marathi_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-16T10:43:09.000Z","likes":0,"trendingScore":0,"private":false,"sha":"a3eded7ad3104f4a294937e5078ef7a254360ac7","downloads":84,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-16T10:31:25.000Z","key":""},{"_id":"67387a7fc36fe6d2f0ddf705","id":"SPRINGLab/SPRING_INX_Marathi_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-12-30T05:34:00.000Z","likes":1,"trendingScore":0,"private":false,"sha":"ba83cc9083c815375b4c3a7ed4c5855ea0d9ae5f","downloads":175,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-16T10:57:03.000Z","key":""},{"_id":"6738850cba93463b5699b57a","id":"SPRINGLab/SPRING_INX_Odia_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-16T11:49:54.000Z","likes":1,"trendingScore":0,"private":false,"sha":"0aee5fd987bf1fc897629a82ce9c328600652999","downloads":289,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-16T11:42:04.000Z","key":""},{"_id":"673888602d8bcd351e510939","id":"SPRINGLab/SPRING_INX_Punjabi_R1","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-16T12:09:07.000Z","likes":0,"trendingScore":0,"private":false,"sha":"97e5f36fce3e24b0ddad726728d1cc4506c24476","downloads":82,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-16T11:56:16.000Z","key":""},{"_id":"6739ade504ba77f721a4e0fd","id":"SPRINGLab/SPRING_INX_Punjabi_R2","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-17T09:08:05.000Z","likes":0,"trendingScore":0,"private":false,"sha":"1cd05ae2e6eff4a91f30b397bfda1826dfb19437","downloads":191,"tags":["size_categories:100K<n<1M","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-17T08:48:37.000Z","key":""},{"_id":"673b4b08955070e4cf7fbc76","id":"SPRINGLab/IndicTTS_Bengali","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-12-30T09:31:48.000Z","likes":3,"trendingScore":0,"private":false,"sha":"3b30a1c5012f15763fe3069e75167e4dd05368e8","description":"\n\t\n\t\t\n\t\tBengali Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Bengali monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Bengali\nTotal Duration: ~15.06 hours (Male: 10.05 hours, Female: 5.01 hours)\nAudio Format: WAV\nSampling Rate:… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Bengali.","downloads":408,"tags":["task_categories:text-to-speech","language:bn","license:cc-by-4.0","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-18T14:11:20.000Z","key":""},{"_id":"673c69659817eb82107e638f","id":"SPRINGLab/IndicVoices-R_Bengali","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-11-30T11:17:08.000Z","likes":0,"trendingScore":0,"private":false,"sha":"0540449f8721bea30e02d43fc8af02703d942023","downloads":145,"tags":["language:bn","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-19T10:33:09.000Z","key":""},{"_id":"67444623329dfb3ee3746b03","id":"SPRINGLab/IndicTTS_Tamil","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-12-30T09:33:36.000Z","likes":4,"trendingScore":0,"private":false,"sha":"6bd9a353470ac39918360ce3169da0b774c9724c","description":"\n\t\n\t\t\n\t\tTamil Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Tamil monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Tamil\nTotal Duration: ~20.33 hours (Male: 10.3 hours, Female: 10.03 hours)\nAudio Format: WAV\nSampling Rate:… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Tamil.","downloads":437,"tags":["task_categories:text-to-speech","language:ta","license:cc-by-4.0","size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-25T09:40:51.000Z","key":""},{"_id":"674451bea784a9d15cc4387c","id":"SPRINGLab/IndicVoices-R_Tamil","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2024-12-01T15:41:51.000Z","likes":3,"trendingScore":0,"private":false,"sha":"7982e64564ad4fff33a7be654a8f69b0b388b760","downloads":475,"tags":["language:ta","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2024-11-25T10:30:22.000Z","key":""},{"_id":"67933e99e4cd9987c9feaff4","id":"SPRINGLab/IndicTTS_Gujarati","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T07:42:39.000Z","likes":3,"trendingScore":0,"private":false,"sha":"ea2b2c26640b8e3e8607b5dcd955cc32424563fb","description":"\n\t\n\t\t\n\t\ttask_categories:\n- text-to-speech\nlanguage:\n- gj\npretty_name: Gujarati Indic TTS dataset\nsize_categories:\n- n<1K\n\t\n\n\n\t\n\t\t\n\t\tGujarati Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Gujarati monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\nGujarati… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Gujarati.","downloads":375,"tags":["size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-24T07:17:45.000Z","key":""},{"_id":"679360f022b48843af91db44","id":"SPRINGLab/IndicTTS_Assamese","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T11:46:39.000Z","likes":0,"trendingScore":0,"private":false,"sha":"2187894443283507696220237bb4f3c21639a69f","description":"\n\t\n\t\t\n\t\tAssamese Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Assamese monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Assamese\nTotal Duration: ~27.4 hours (Male: 5.16 hours, Female: 5.18 hours)\nAudio Format: WAV\nSampling Rate:… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Assamese.","downloads":131,"tags":["task_categories:text-to-speech","language:as","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-24T09:44:16.000Z","key":""},{"_id":"67937b76eb1634136e329d4c","id":"SPRINGLab/IndicTTS_Kannada","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-25T05:52:49.000Z","likes":4,"trendingScore":0,"private":false,"sha":"2ec438c4d144855ed6195d4aaefbda94bf896d2f","description":"\n\t\n\t\t\n\t\tKannada Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Kannada monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Kannada\nTotal Duration: ~7.35 hours (Male: 3.4 hours, Female: 3.95 hours)\nAudio Format: WAV\nSampling Rate:… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Kannada.","downloads":206,"tags":["task_categories:text-to-speech","language:kn","size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-24T11:37:26.000Z","key":""},{"_id":"679383b607f0238a0d7c557e","id":"SPRINGLab/IndicTTS_Malayalam","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-25T05:52:03.000Z","likes":2,"trendingScore":0,"private":false,"sha":"f67d76ac5e768274c7260c2f22f8044bc2972fe5","description":"\n\t\n\t\t\n\t\tMalayalam Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Malayalam monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Malayalam\nTotal Duration: ~17.89 hours (Male: 9.7 hours, Female: 8.19 hours)\nAudio Format: WAV\nSampling… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Malayalam.","downloads":131,"tags":["task_categories:text-to-speech","language:ml","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-24T12:12:38.000Z","key":""},{"_id":"679395b1cb91193a3977f762","id":"SPRINGLab/IndicTTS_Marathi","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T10:14:02.000Z","likes":1,"trendingScore":0,"private":false,"sha":"53ee367088c223405d8e5e485cf30cc1f47249ba","description":"\n\t\n\t\t\n\t\tMarathi Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Marathi monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Marathi\nTotal Duration: ~10.33 hours (Male: 5.16 hours, Female: 5.18 hours)\nAudio Format: WAV\nSampling Rate:… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Marathi.","downloads":302,"tags":["task_categories:text-to-speech","language:mr","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-24T13:29:21.000Z","key":""},{"_id":"679756bed4afc6fb1ca28c91","id":"SPRINGLab/IndicTTS_Punjabi","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T10:13:08.000Z","likes":6,"trendingScore":0,"private":false,"sha":"21c3b1f0340a6fbdb5483e9dd1781ec45cc0cd90","description":"\n\t\n\t\t\n\t\tPunjabi Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Punjabi monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Punjabi\nTotal Duration: ~20 hours (Male: 10 hours, Female: 10 hours)\nAudio Format: WAV\nSampling Rate: 48000Hz… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Punjabi.","downloads":89,"tags":["task_categories:text-to-speech","language:pb","license:cc-by-4.0","size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-27T09:49:50.000Z","key":""},{"_id":"67976357fd3e00bda6a25ff6","id":"SPRINGLab/IndicTTS_Rajasthani","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T10:54:36.000Z","likes":0,"trendingScore":0,"private":false,"sha":"ba808bd87a851806d99e54ee99f93318f8d80806","description":"\n\t\n\t\t\n\t\tRajasthani Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Rajasthani monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Rajasthani\nTotal Duration: ~20.06hours (Male: 9.82 hours, Female: 10.24 hours)\nAudio Format: WAV… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Rajasthani.","downloads":62,"tags":["task_categories:text-to-speech","language:rj","size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-27T10:43:35.000Z","key":""},{"_id":"6797689420c7240ced8938aa","id":"SPRINGLab/IndicTTS_Odia","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T11:36:49.000Z","likes":1,"trendingScore":0,"private":false,"sha":"c7547a780b09b5c2f9eb47aa07544088aa75e766","description":"\n\t\n\t\t\n\t\tOdia Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Odia monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Odia\nTotal Duration: ~8.74 hours (Male: 4.47 hours, Female: 4.27 hours)\nAudio Format: WAV\nSampling Rate: 48000Hz… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Odia.","downloads":125,"tags":["task_categories:text-to-speech","language:od","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-27T11:05:56.000Z","key":""},{"_id":"6797efb2e05ca91d7efa8228","id":"SPRINGLab/IndicTTS_Telugu","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-01-27T21:07:32.000Z","likes":7,"trendingScore":0,"private":false,"sha":"7ab3c18491bef3f5d4e820c2701b5f78f54031d6","description":"\n\t\n\t\t\n\t\tTelugu Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Telugu monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Telugu\nTotal Duration: ~8.74 hours (Male: 4.47 hours, Female: 4.27 hours)\nAudio Format: WAV\nSampling Rate:… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Telugu.","downloads":320,"tags":["task_categories:text-to-speech","language:te","size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-27T20:42:26.000Z","key":""},{"_id":"679a05d69a598f965c048ef9","id":"SPRINGLab/IndicTTS_Manipuri","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-06-26T07:05:03.000Z","likes":2,"trendingScore":0,"private":false,"sha":"a7472c5ec603e22a9ab1f1d52aa44e2b23b24d14","description":"\n\t\n\t\t\n\t\tManipuri Indic TTS Dataset\n\t\n\nThis dataset is derived from the Indic TTS Database project, specifically using the Manipuri monolingual recordings from both male and female speakers. The dataset contains high-quality speech recordings with corresponding text transcriptions, making it suitable for text-to-speech (TTS) research and development.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\nLanguage: Manipuri\nTotal Duration: ~20.75 hours (Male: 10.61 hours, Female: 10.14 hours)\nAudio Format: WAV\nSampling… See the full description on the dataset page: https://huggingface.co/datasets/SPRINGLab/IndicTTS_Manipuri.","downloads":94,"tags":["task_categories:text-to-speech","language:mni","size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-01-29T10:41:26.000Z","key":""},{"_id":"68e377b2eec74296e792a933","id":"SPRINGLab/libri960","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-10-06T08:04:48.000Z","likes":0,"trendingScore":0,"private":false,"sha":"d7fcb1e0bf4305a0f63943f2721dc61bd1c32304","downloads":96,"tags":["size_categories:100K<n<1M","format:arrow","modality:audio","modality:text","library:datasets","library:mlcroissant","region:us"],"createdAt":"2025-10-06T08:02:58.000Z","key":""},{"_id":"68ebebef652c28ca3b384a91","id":"SPRINGLab/LibriSpeech-100","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-10-12T18:17:39.000Z","likes":2,"trendingScore":0,"private":false,"sha":"c9c03efabb3ccf308018a18e20342158733d7e00","downloads":53,"tags":["size_categories:10K<n<100K","format:parquet","modality:audio","modality:text","library:datasets","library:dask","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-10-12T17:57:03.000Z","key":""},{"_id":"68ebf31d163924d46391e583","id":"SPRINGLab/LibriSpeech-Dev","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-10-12T18:34:04.000Z","likes":0,"trendingScore":0,"private":false,"sha":"4cdf32a547bf407d39a11a8f255de911fe43848d","downloads":18,"tags":["size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:pandas","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-10-12T18:27:41.000Z","key":""},{"_id":"68ebf32a1c9d646141183ca4","id":"SPRINGLab/LibriSpeech-Test","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2025-10-12T18:33:41.000Z","likes":0,"trendingScore":0,"private":false,"sha":"1b36c842d6afa3a2eaf8cb91be78a840ba8dd6dd","downloads":57,"tags":["size_categories:1K<n<10K","format:parquet","modality:audio","modality:text","library:datasets","library:pandas","library:mlcroissant","library:polars","region:us"],"createdAt":"2025-10-12T18:27:54.000Z","key":""},{"_id":"69c2b1551a8cc9ac29889f5d","id":"SPRINGLab/w2v-exercise","author":"SPRINGLab","disabled":false,"gated":false,"lastModified":"2026-03-24T15:44:35.000Z","likes":0,"trendingScore":0,"private":false,"sha":"222ff394240b003a5cdd211ad9760565c19c6f4c","downloads":26,"tags":["size_categories:1K<n<10K","format:parquet","format:optimized-parquet","modality:audio","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us"],"createdAt":"2026-03-24T15:44:21.000Z","key":""}]