Upload folder using huggingface_hub

examples/aishell_asr_zh_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8ed27441c9a5f6ac8b38e27b52ce555fe03322530ff16c16f2796c9f6e7f45
+size 44296

examples/aishell_asr_zh_test/dataset_info.json

@@ -0,0 +1,58 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "aishell_asr_zh_test_v1",
+  "dataset_size": 1115469955,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/aishell_asr_zh_test_v1@e73dc7f096ecea5c8e5c722446c8d3b4014fdd18/data/test-00000-of-00003.parquet": {
+      "num_bytes": 364047728,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/aishell_asr_zh_test_v1@e73dc7f096ecea5c8e5c722446c8d3b4014fdd18/data/test-00001-of-00003.parquet": {
+      "num_bytes": 354834886,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/aishell_asr_zh_test_v1@e73dc7f096ecea5c8e5c722446c8d3b4014fdd18/data/test-00002-of-00003.parquet": {
+      "num_bytes": 377041689,
+      "checksum": null
+    }
+  },
+  "download_size": 1095924303,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 2211394258,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 1115469955,
+      "num_examples": 6920,
+      "shard_lengths": [
+        3207,
+        3107,
+        606
+      ],
+      "dataset_name": "aishell_asr_zh_test_v1"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/aishell_asr_zh_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "5a1f0f8b9b3ca365",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/alpaca_audio_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbe0fbf69f6732a358e6c6575354464b9c5e39b87be73cc9f1ae7c284e9e575
+size 44600

examples/alpaca_audio_test/dataset_info.json

@@ -0,0 +1,49 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "alpaca_audio_test",
+  "dataset_size": 13865321,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/alpaca_audio_test@7eb2ab279975033690d67bee66e45eb612a430ee/data/test-00000-of-00001.parquet": {
+      "num_bytes": 12245608,
+      "checksum": null
+    }
+  },
+  "download_size": 12245608,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "speech_instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 26110929,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 13865321,
+      "num_examples": 100,
+      "dataset_name": "alpaca_audio_test"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/alpaca_audio_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "a7169220e58f4523",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/audiocaps_qa_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4745b0e32ece9d9f32f5a5a689eb5e24ca6755f114cd2b1f1f445819fa1375
+size 103208

examples/audiocaps_qa_test/dataset_info.json

@@ -0,0 +1,45 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "audiocaps_qa_test_v3",
+  "dataset_size": 98835422,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/audiocaps_qa_test_v3@6cf6853c52f55482126f226a8859eb71f2021e0e/data/test-00000-of-00001.parquet": {
+      "num_bytes": 92241687,
+      "checksum": null
+    }
+  },
+  "download_size": 92241687,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 191077109,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 98835422,
+      "num_examples": 313,
+      "dataset_name": "audiocaps_qa_test_v3"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/audiocaps_qa_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "748c6693112f77f2",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/audiocaps_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cfff9093667c39e6750f23693d4d817193a0fbb829e3c6155d4a4c44462a184
+size 107320

examples/audiocaps_test/dataset_info.json

@@ -0,0 +1,58 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "audiocaps_test",
+  "dataset_size": 1389113784,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/audiocaps_test@fb42aac15212cbddd723fbbf04b6071b60a9f8fe/data/test-00000-of-00003.parquet": {
+      "num_bytes": 432299885,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/audiocaps_test@fb42aac15212cbddd723fbbf04b6071b60a9f8fe/data/test-00001-of-00003.parquet": {
+      "num_bytes": 435786346,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/audiocaps_test@fb42aac15212cbddd723fbbf04b6071b60a9f8fe/data/test-00002-of-00003.parquet": {
+      "num_bytes": 435930887,
+      "checksum": null
+    }
+  },
+  "download_size": 1304017118,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 2693130902,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 1389113784,
+      "num_examples": 4400,
+      "shard_lengths": [
+        1667,
+        1667,
+        1066
+      ],
+      "dataset_name": "audiocaps_test"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/audiocaps_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "1872292586a4b460",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/clotho_aqa_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad7fcb1e24f43a32efd32f08888b84f2ff5ebd275e43ca26e6230c7d01922cf
+size 194400

examples/clotho_aqa_test/dataset_info.json

@@ -0,0 +1,58 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "clotho_asqa_test_v2",
+  "dataset_size": 1485321871,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/clotho_asqa_test_v2@a7f4a7983d490e87a79eb041fede83e418c0ea4f/data/test-00000-of-00003.parquet": {
+      "num_bytes": 118559858,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/clotho_asqa_test_v2@a7f4a7983d490e87a79eb041fede83e418c0ea4f/data/test-00001-of-00003.parquet": {
+      "num_bytes": 116519615,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/clotho_asqa_test_v2@a7f4a7983d490e87a79eb041fede83e418c0ea4f/data/test-00002-of-00003.parquet": {
+      "num_bytes": 113032047,
+      "checksum": null
+    }
+  },
+  "download_size": 348111520,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 1833433391,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 1485321871,
+      "num_examples": 2057,
+      "shard_lengths": [
+        786,
+        786,
+        485
+      ],
+      "dataset_name": "clotho_asqa_test_v2"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/clotho_aqa_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "35d1627b19106626",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/cn_college_listen_mcq_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3131dbbd9306a9622d446f8f151f1db0dd7ba3a14bd82f711126d159a813d5d5
+size 152776

examples/cn_college_listen_mcq_test/dataset_info.json

@@ -0,0 +1,66 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "cn_college_listen_mcq_test",
+  "dataset_size": 1532841284,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/cn_college_listen_mcq_test@708d8ef278b5eadae714c314889f5d81ded18a25/data/test-00000-of-00004.parquet": {
+      "num_bytes": 283046288,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/cn_college_listen_mcq_test@708d8ef278b5eadae714c314889f5d81ded18a25/data/test-00001-of-00004.parquet": {
+      "num_bytes": 241939389,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/cn_college_listen_mcq_test@708d8ef278b5eadae714c314889f5d81ded18a25/data/test-00002-of-00004.parquet": {
+      "num_bytes": 248376444,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/cn_college_listen_mcq_test@708d8ef278b5eadae714c314889f5d81ded18a25/data/test-00003-of-00004.parquet": {
+      "num_bytes": 256294919,
+      "checksum": null
+    }
+  },
+  "download_size": 1029657040,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "choices": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 2562498324,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 1532841284,
+      "num_examples": 2271,
+      "shard_lengths": [
+        500,
+        1036,
+        735
+      ],
+      "dataset_name": "cn_college_listen_mcq_test"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/cn_college_listen_mcq_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "d42e39c8837074fc",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/cna_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37e6858c1291ebeb2bcb6bfbe8f5291da48f4199a46ae88a60eb57fa135b61f
+size 34600

examples/cna_test/dataset_info.json

@@ -0,0 +1,20 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/cna_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "22ae0abf541af796",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/common_voice_15_en_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5f49efa47828a4a7b9a6fc584b19562acae2f90451219939b0c11b4d41621f
+size 54992

examples/common_voice_15_en_test/dataset_info.json

@@ -0,0 +1,28 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "language": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "audio_length": {
+      "dtype": "float64",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/common_voice_15_en_test/state.json

@@ -0,0 +1,19 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "62012827f888a0f5",
+  "_format_columns": [
+    "answer",
+    "audio_length",
+    "context",
+    "instruction",
+    "language"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/commonvoice_17_id_asr/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae05a4b823184603908f2b4149190b4fab9965be5468f6b4fa34e0e214c97760
+size 43784

examples/commonvoice_17_id_asr/dataset_info.json

@@ -0,0 +1,132 @@
+{
+  "builder_name": "common_voice_17_0",
+  "citation": "@inproceedings{commonvoice:2020,\n  author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.},\n  title = {Common Voice: A Massively-Multilingual Speech Corpus},\n  booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)},\n  pages = {4211--4215},\n  year = 2020\n}\n",
+  "config_name": "id",
+  "dataset_name": "common_voice_17_0",
+  "dataset_size": 42157018,
+  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 20408 validated hours of speech  in 124 languages, but more voices and languages are always added.",
+  "download_checksums": {
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/n_shards.json": {
+      "num_bytes": 17491,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/id/train/id_train_0.tar": {
+      "num_bytes": 170035200,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/id/dev/id_dev_0.tar": {
+      "num_bytes": 102236160,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/id/test/id_test_0.tar": {
+      "num_bytes": 110315520,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/id/other/id_other_0.tar": {
+      "num_bytes": 686858240,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/id/invalidated/id_invalidated_0.tar": {
+      "num_bytes": 68034560,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/id/validated/id_validated_0.tar": {
+      "num_bytes": 805611520,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/id/train.tsv": {
+      "num_bytes": 1571021,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/id/dev.tsv": {
+      "num_bytes": 1016964,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/id/test.tsv": {
+      "num_bytes": 1052525,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/id/other.tsv": {
+      "num_bytes": 8607181,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/id/invalidated.tsv": {
+      "num_bytes": 784798,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/id/validated.tsv": {
+      "num_bytes": 7772548,
+      "checksum": null
+    }
+  },
+  "download_size": 1963913728,
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "audio_length": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "language": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "https://commonvoice.mozilla.org/en/datasets",
+  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
+  "size_in_bytes": 2006070746,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 3067499,
+      "num_examples": 4970,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validation": {
+      "name": "validation",
+      "num_bytes": 2011909,
+      "num_examples": 3349,
+      "dataset_name": "common_voice_17_0"
+    },
+    "test": {
+      "name": "test",
+      "num_bytes": 2141524,
+      "num_examples": 3641,
+      "dataset_name": "common_voice_17_0"
+    },
+    "other": {
+      "name": "other",
+      "num_bytes": 17492664,
+      "num_examples": 29508,
+      "dataset_name": "common_voice_17_0"
+    },
+    "invalidated": {
+      "name": "invalidated",
+      "num_bytes": 1600375,
+      "num_examples": 2605,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validated": {
+      "name": "validated",
+      "num_bytes": 15843047,
+      "num_examples": 26108,
+      "dataset_name": "common_voice_17_0"
+    }
+  },
+  "version": {
+    "version_str": "17.0.0",
+    "major": 17,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/commonvoice_17_id_asr/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "75931a254b089787",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/commonvoice_17_ta_asr/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98470c84b50bb5c1b10476e4f6ea518ddd9127b64b0c680302f774af7b538b71
+size 90616

examples/commonvoice_17_ta_asr/dataset_info.json

@@ -0,0 +1,156 @@
+{
+  "builder_name": "common_voice_17_0",
+  "citation": "@inproceedings{commonvoice:2020,\n  author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.},\n  title = {Common Voice: A Massively-Multilingual Speech Corpus},\n  booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)},\n  pages = {4211--4215},\n  year = 2020\n}\n",
+  "config_name": "ta",
+  "dataset_name": "common_voice_17_0",
+  "dataset_size": 221361139,
+  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 20408 validated hours of speech  in 124 languages, but more voices and languages are always added.",
+  "download_checksums": {
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/n_shards.json": {
+      "num_bytes": 17491,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/train/ta_train_0.tar": {
+      "num_bytes": 1598955520,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/train/ta_train_1.tar": {
+      "num_bytes": 224542720,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/dev/ta_dev_0.tar": {
+      "num_bytes": 434257920,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/test/ta_test_0.tar": {
+      "num_bytes": 454778880,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/other/ta_other_0.tar": {
+      "num_bytes": 1560514560,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/other/ta_other_1.tar": {
+      "num_bytes": 1515827200,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/other/ta_other_2.tar": {
+      "num_bytes": 495831040,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/invalidated/ta_invalidated_0.tar": {
+      "num_bytes": 231424000,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_0.tar": {
+      "num_bytes": 1447434240,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_1.tar": {
+      "num_bytes": 1530644480,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_2.tar": {
+      "num_bytes": 1654978560,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_3.tar": {
+      "num_bytes": 652861440,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/train.tsv": {
+      "num_bytes": 19608830,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/dev.tsv": {
+      "num_bytes": 5203704,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/test.tsv": {
+      "num_bytes": 4944646,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/other.tsv": {
+      "num_bytes": 39470943,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/invalidated.tsv": {
+      "num_bytes": 2499761,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/validated.tsv": {
+      "num_bytes": 56763398,
+      "checksum": null
+    }
+  },
+  "download_size": 11930559333,
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "audio_length": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "language": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "https://commonvoice.mozilla.org/en/datasets",
+  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
+  "size_in_bytes": 12151920472,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 33336098,
+      "num_examples": 45587,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validation": {
+      "name": "validation",
+      "num_bytes": 8797317,
+      "num_examples": 12095,
+      "dataset_name": "common_voice_17_0"
+    },
+    "test": {
+      "name": "test",
+      "num_bytes": 8556167,
+      "num_examples": 12074,
+      "dataset_name": "common_voice_17_0"
+    },
+    "other": {
+      "name": "other",
+      "num_bytes": 67773267,
+      "num_examples": 93989,
+      "dataset_name": "common_voice_17_0"
+    },
+    "invalidated": {
+      "name": "invalidated",
+      "num_bytes": 4282268,
+      "num_examples": 5693,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validated": {
+      "name": "validated",
+      "num_bytes": 98616022,
+      "num_examples": 135391,
+      "dataset_name": "common_voice_17_0"
+    }
+  },
+  "version": {
+    "version_str": "17.0.0",
+    "major": 17,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/commonvoice_17_ta_asr/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "380f8a99e8b3657c",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/commonvoice_17_th_asr/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd84989250d4b79f4cb4b0ae5028d032e221858d6dab77494a04a8a2336aab4
+size 44792

examples/commonvoice_17_th_asr/dataset_info.json

@@ -0,0 +1,164 @@
+{
+  "builder_name": "common_voice_17_0",
+  "citation": "@inproceedings{commonvoice:2020,\n  author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.},\n  title = {Common Voice: A Massively-Multilingual Speech Corpus},\n  booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)},\n  pages = {4211--4215},\n  year = 2020\n}\n",
+  "config_name": "th",
+  "dataset_name": "common_voice_17_0",
+  "dataset_size": 271837409,
+  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 20408 validated hours of speech  in 124 languages, but more voices and languages are always added.",
+  "download_checksums": {
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/n_shards.json": {
+      "num_bytes": 17491,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/train/th_train_0.tar": {
+      "num_bytes": 838082560,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/dev/th_dev_0.tar": {
+      "num_bytes": 323399680,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/test/th_test_0.tar": {
+      "num_bytes": 335851520,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_0.tar": {
+      "num_bytes": 1147064320,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_1.tar": {
+      "num_bytes": 1057300480,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_2.tar": {
+      "num_bytes": 943237120,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_3.tar": {
+      "num_bytes": 837079040,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_4.tar": {
+      "num_bytes": 1055385600,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_5.tar": {
+      "num_bytes": 176015360,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/invalidated/th_invalidated_0.tar": {
+      "num_bytes": 287416320,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_0.tar": {
+      "num_bytes": 1191843840,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_1.tar": {
+      "num_bytes": 1079930880,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_2.tar": {
+      "num_bytes": 1014691840,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_3.tar": {
+      "num_bytes": 744366080,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/train.tsv": {
+      "num_bytes": 11337047,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/dev.tsv": {
+      "num_bytes": 3803758,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/test.tsv": {
+      "num_bytes": 3702050,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/other.tsv": {
+      "num_bytes": 71870764,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/invalidated.tsv": {
+      "num_bytes": 3301372,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/validated.tsv": {
+      "num_bytes": 50649618,
+      "checksum": null
+    }
+  },
+  "download_size": 11176346740,
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "audio_length": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "language": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "https://commonvoice.mozilla.org/en/datasets",
+  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
+  "size_in_bytes": 11448184149,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 21220759,
+      "num_examples": 32823,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validation": {
+      "name": "validation",
+      "num_bytes": 7084499,
+      "num_examples": 11042,
+      "dataset_name": "common_voice_17_0"
+    },
+    "test": {
+      "name": "test",
+      "num_bytes": 7004874,
+      "num_examples": 11042,
+      "dataset_name": "common_voice_17_0"
+    },
+    "other": {
+      "name": "other",
+      "num_bytes": 134183952,
+      "num_examples": 206935,
+      "dataset_name": "common_voice_17_0"
+    },
+    "invalidated": {
+      "name": "invalidated",
+      "num_bytes": 6202988,
+      "num_examples": 9267,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validated": {
+      "name": "validated",
+      "num_bytes": 96140337,
+      "num_examples": 147160,
+      "dataset_name": "common_voice_17_0"
+    }
+  },
+  "version": {
+    "version_str": "17.0.0",
+    "major": 17,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/commonvoice_17_th_asr/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "4b0c4a31664c7d67",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/commonvoice_17_vi_asr/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4249665ed76ad59af6281a9c0bacc6862d8cd750218637cd8570bc9d89002751
+size 39104

examples/commonvoice_17_vi_asr/dataset_info.json

@@ -0,0 +1,132 @@
+{
+  "builder_name": "common_voice_17_0",
+  "citation": "@inproceedings{commonvoice:2020,\n  author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.},\n  title = {Common Voice: A Massively-Multilingual Speech Corpus},\n  booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)},\n  pages = {4211--4215},\n  year = 2020\n}\n",
+  "config_name": "vi",
+  "dataset_name": "common_voice_17_0",
+  "dataset_size": 12705254,
+  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 20408 validated hours of speech  in 124 languages, but more voices and languages are always added.",
+  "download_checksums": {
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/n_shards.json": {
+      "num_bytes": 17491,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/train/vi_train_0.tar": {
+      "num_bytes": 69468160,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/dev/vi_dev_0.tar": {
+      "num_bytes": 14479360,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/test/vi_test_0.tar": {
+      "num_bytes": 34488320,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/other/vi_other_0.tar": {
+      "num_bytes": 276172800,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/invalidated/vi_invalidated_0.tar": {
+      "num_bytes": 11345920,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/validated/vi_validated_0.tar": {
+      "num_bytes": 144384000,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/train.tsv": {
+      "num_bytes": 688189,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/dev.tsv": {
+      "num_bytes": 184767,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/test.tsv": {
+      "num_bytes": 373370,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/other.tsv": {
+      "num_bytes": 3384906,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/invalidated.tsv": {
+      "num_bytes": 111099,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/validated.tsv": {
+      "num_bytes": 1521796,
+      "checksum": null
+    }
+  },
+  "download_size": 556620178,
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "audio_length": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "language": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "https://commonvoice.mozilla.org/en/datasets",
+  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
+  "size_in_bytes": 569325432,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 1380061,
+      "num_examples": 2298,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validation": {
+      "name": "validation",
+      "num_bytes": 375111,
+      "num_examples": 641,
+      "dataset_name": "common_voice_17_0"
+    },
+    "test": {
+      "name": "test",
+      "num_bytes": 754342,
+      "num_examples": 1274,
+      "dataset_name": "common_voice_17_0"
+    },
+    "other": {
+      "name": "other",
+      "num_bytes": 6857667,
+      "num_examples": 11533,
+      "dataset_name": "common_voice_17_0"
+    },
+    "invalidated": {
+      "name": "invalidated",
+      "num_bytes": 229034,
+      "num_examples": 377,
+      "dataset_name": "common_voice_17_0"
+    },
+    "validated": {
+      "name": "validated",
+      "num_bytes": 3109039,
+      "num_examples": 5135,
+      "dataset_name": "common_voice_17_0"
+    }
+  },
+  "version": {
+    "version_str": "17.0.0",
+    "major": 17,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/commonvoice_17_vi_asr/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "6ce07a66a0e6d7b0",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/commonvoice_zh_asr/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951bb47527709c895c17e6dac4a4a43b2a141b16babd39e56d9199deaec72eb5
+size 68224

examples/commonvoice_zh_asr/dataset_info.json

@@ -0,0 +1,182 @@
+{
+  "builder_name": "common_voice_16_0",
+  "citation": "@inproceedings{commonvoice:2020,\n  author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.},\n  title = {Common Voice: A Massively-Multilingual Speech Corpus},\n  booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)},\n  pages = {4211--4215},\n  year = 2020\n}\n",
+  "config_name": "zh-CN",
+  "dataset_name": "common_voice_16_0",
+  "dataset_size": 423983727,
+  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 19159 validated hours of speech  in 119 languages, but more voices and languages are always added.",
+  "download_checksums": {
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/n_shards.json": {
+      "num_bytes": 17487,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/train/zh-CN_train_0.tar": {
+      "num_bytes": 1157220864,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/dev/zh-CN_dev_0.tar": {
+      "num_bytes": 436442624,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/test/zh-CN_test_0.tar": {
+      "num_bytes": 506296320,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_0.tar": {
+      "num_bytes": 1252570624,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_1.tar": {
+      "num_bytes": 1216365056,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_2.tar": {
+      "num_bytes": 1057693696,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_3.tar": {
+      "num_bytes": 1037878784,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_4.tar": {
+      "num_bytes": 1006488064,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_5.tar": {
+      "num_bytes": 951297024,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_6.tar": {
+      "num_bytes": 1054305280,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_7.tar": {
+      "num_bytes": 1079122944,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_8.tar": {
+      "num_bytes": 1057605632,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_9.tar": {
+      "num_bytes": 1054744064,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_10.tar": {
+      "num_bytes": 1037184512,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_11.tar": {
+      "num_bytes": 1081821184,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_12.tar": {
+      "num_bytes": 1144596992,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_13.tar": {
+      "num_bytes": 1211527680,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_14.tar": {
+      "num_bytes": 1190928384,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_15.tar": {
+      "num_bytes": 299709952,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/invalidated/zh-CN_invalidated_0.tar": {
+      "num_bytes": 1000983552,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/invalidated/zh-CN_invalidated_1.tar": {
+      "num_bytes": 416471552,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/train.tsv": {
+      "num_bytes": 7373507,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/dev.tsv": {
+      "num_bytes": 2567399,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/test.tsv": {
+      "num_bytes": 2457920,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/other.tsv": {
+      "num_bytes": 137605043,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/invalidated.tsv": {
+      "num_bytes": 13622503,
+      "checksum": null
+    }
+  },
+  "download_size": 20414898643,
+  "features": {
+    "context": {
+      "sampling_rate": 16000,
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "audio_length": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "language": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "https://commonvoice.mozilla.org/en/datasets",
+  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
+  "size_in_bytes": 20838882370,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 17963235,
+      "num_examples": 29406,
+      "dataset_name": "common_voice_16_0"
+    },
+    "validation": {
+      "name": "validation",
+      "num_bytes": 6351483,
+      "num_examples": 10626,
+      "dataset_name": "common_voice_16_0"
+    },
+    "test": {
+      "name": "test",
+      "num_bytes": 6263265,
+      "num_examples": 10626,
+      "dataset_name": "common_voice_16_0"
+    },
+    "other": {
+      "name": "other",
+      "num_bytes": 358056452,
+      "num_examples": 610981,
+      "dataset_name": "common_voice_16_0"
+    },
+    "invalidated": {
+      "name": "invalidated",
+      "num_bytes": 35349292,
+      "num_examples": 58386,
+      "dataset_name": "common_voice_16_0"
+    }
+  },
+  "version": {
+    "version_str": "15.0.0",
+    "major": 15,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/commonvoice_zh_asr/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "41452271d4051e81",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/covost2_en_id_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4bfb1098a59bf75aab6b9b824141808bb48160787b182b03fabf4a56527a9e
+size 56496

examples/covost2_en_id_test/dataset_info.json

@@ -0,0 +1,73 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "covost2_en_id_test_v1",
+  "dataset_size": 2842304040,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/covost2_en_id_test_v1@51a4b1517f07e1dcf9180aa270f264961165cab3/data/test-00000-of-00006.parquet": {
+      "num_bytes": 421383822,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_id_test_v1@51a4b1517f07e1dcf9180aa270f264961165cab3/data/test-00001-of-00006.parquet": {
+      "num_bytes": 430366828,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_id_test_v1@51a4b1517f07e1dcf9180aa270f264961165cab3/data/test-00002-of-00006.parquet": {
+      "num_bytes": 423203231,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_id_test_v1@51a4b1517f07e1dcf9180aa270f264961165cab3/data/test-00003-of-00006.parquet": {
+      "num_bytes": 420946330,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_id_test_v1@51a4b1517f07e1dcf9180aa270f264961165cab3/data/test-00004-of-00006.parquet": {
+      "num_bytes": 419734090,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_id_test_v1@51a4b1517f07e1dcf9180aa270f264961165cab3/data/test-00005-of-00006.parquet": {
+      "num_bytes": 419963769,
+      "checksum": null
+    }
+  },
+  "download_size": 2535598070,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 5377902110,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 2842304040,
+      "num_examples": 15531,
+      "shard_lengths": [
+        2789,
+        2789,
+        2789,
+        2788,
+        2788,
+        1588
+      ],
+      "dataset_name": "covost2_en_id_test_v1"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/covost2_en_id_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "f755c8fc2cb9504a",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/covost2_en_ta_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89aa8cee7fa6754a1491ca48e31162126a808e07bca8731ecf2949bc183dd20f
+size 58088

examples/covost2_en_ta_test/dataset_info.json

@@ -0,0 +1,73 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "covost2_en_ta_test_v1",
+  "dataset_size": 2844002846,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/covost2_en_ta_test_v1@23c23a71d698faf6c940e18753ade03acbcef86b/data/test-00000-of-00006.parquet": {
+      "num_bytes": 421472102,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_ta_test_v1@23c23a71d698faf6c940e18753ade03acbcef86b/data/test-00001-of-00006.parquet": {
+      "num_bytes": 430453377,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_ta_test_v1@23c23a71d698faf6c940e18753ade03acbcef86b/data/test-00002-of-00006.parquet": {
+      "num_bytes": 423289725,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_ta_test_v1@23c23a71d698faf6c940e18753ade03acbcef86b/data/test-00003-of-00006.parquet": {
+      "num_bytes": 421032929,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_ta_test_v1@23c23a71d698faf6c940e18753ade03acbcef86b/data/test-00004-of-00006.parquet": {
+      "num_bytes": 419820665,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_ta_test_v1@23c23a71d698faf6c940e18753ade03acbcef86b/data/test-00005-of-00006.parquet": {
+      "num_bytes": 420052504,
+      "checksum": null
+    }
+  },
+  "download_size": 2536121302,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 5380124148,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 2844002846,
+      "num_examples": 15531,
+      "shard_lengths": [
+        2789,
+        2789,
+        2789,
+        2788,
+        2788,
+        1588
+      ],
+      "dataset_name": "covost2_en_ta_test_v1"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/covost2_en_ta_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "fe170901fd58bb52",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/covost2_en_zh_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca2fa905173efcf428fd779b4e74ff132b8bab979f925e75ad7ff8b9b19aaa8
+size 40016

examples/covost2_en_zh_test/dataset_info.json

@@ -0,0 +1,73 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "covost2_en_zh_test_v1",
+  "dataset_size": 2842110316,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/covost2_en_zh_test_v1@6fe92d7fabaee215b078b022abbe8959280f3187/data/test-00000-of-00006.parquet": {
+      "num_bytes": 421376507,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_zh_test_v1@6fe92d7fabaee215b078b022abbe8959280f3187/data/test-00001-of-00006.parquet": {
+      "num_bytes": 430362096,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_zh_test_v1@6fe92d7fabaee215b078b022abbe8959280f3187/data/test-00002-of-00006.parquet": {
+      "num_bytes": 423196814,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_zh_test_v1@6fe92d7fabaee215b078b022abbe8959280f3187/data/test-00003-of-00006.parquet": {
+      "num_bytes": 420938958,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_zh_test_v1@6fe92d7fabaee215b078b022abbe8959280f3187/data/test-00004-of-00006.parquet": {
+      "num_bytes": 419730286,
+      "checksum": null
+    },
+    "hf://datasets/AudioLLMs/covost2_en_zh_test_v1@6fe92d7fabaee215b078b022abbe8959280f3187/data/test-00005-of-00006.parquet": {
+      "num_bytes": 419958145,
+      "checksum": null
+    }
+  },
+  "download_size": 2535562806,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 5377673122,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 2842110316,
+      "num_examples": 15531,
+      "shard_lengths": [
+        2789,
+        2789,
+        2789,
+        2788,
+        2788,
+        1588
+      ],
+      "dataset_name": "covost2_en_zh_test_v1"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

examples/covost2_en_zh_test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "7445fef56d00d00b",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/covost2_id_en_test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573589410f93a7667f83d37bd30b472069e7446d2d5e05aa98fc4138b0fd316b
+size 50736

examples/covost2_id_en_test/dataset_info.json

@@ -0,0 +1,45 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "covost2_id_en_test_v1",
+  "dataset_size": 105217105,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/AudioLLMs/covost2_id_en_test_v1@3998e50bec6eefdae5b38278238c359acb583f4c/data/test-00000-of-00001.parquet": {
+      "num_bytes": 100225392,
+      "checksum": null
+    }
+  },
+  "download_size": 100225392,
+  "features": {
+    "context": {
+      "_type": "Audio"
+    },
+    "instruction": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "answer": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 205442497,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 105217105,
+      "num_examples": 844,
+      "dataset_name": "covost2_id_en_test_v1"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}