This {component_name.lower()} is based on - MERaLiON-AudioLLM, - developed by I2R, A*STAR, in collaboration with AISG, Singapore. - {description}
diff --git a/README.md b/README.md index 8a00bb12a279eee5165d19eb79bef0c8c3e02ba9..bc366c8faab51bf7ea525a3ee829ef357225f516 100644 --- a/README.md +++ b/README.md @@ -3,12 +3,11 @@ title: Interactive-Demo / MERaLiON-AudioLLM emoji: 🚀 colorFrom: indigo colorTo: indigo -sdk: streamlit -sdk_version: 1.41.1 -app_file: app.py +sdk: static pinned: true models: +- MERaLiON/MERaLiON-2-10B +- MERaLiON/MERaLiON-2-10B-ASR - MERaLiON/MERaLiON-AudioLLM-Whisper-SEA-LION --- -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/app.py b/app.py deleted file mode 100644 index e497863323cffda8c0dcd856a502419068d5c166..0000000000000000000000000000000000000000 --- a/app.py +++ /dev/null @@ -1,3 +0,0 @@ -from src.content.playground import playground_page - -playground_page() \ No newline at end of file diff --git a/audio_samples/10_ASR_IMDA_PART4_30_ASR_v2_1527.wav b/audio_samples/10_ASR_IMDA_PART4_30_ASR_v2_1527.wav deleted file mode 100644 index d1fa45ef18df244757240868794d54063f723d56..0000000000000000000000000000000000000000 Binary files a/audio_samples/10_ASR_IMDA_PART4_30_ASR_v2_1527.wav and /dev/null differ diff --git a/audio_samples/11_ASR_IMDA_PART4_30_ASR_v2_3771.wav b/audio_samples/11_ASR_IMDA_PART4_30_ASR_v2_3771.wav deleted file mode 100644 index f8c81dfdd16b9167a273a3964a6a3dd47de80d98..0000000000000000000000000000000000000000 Binary files a/audio_samples/11_ASR_IMDA_PART4_30_ASR_v2_3771.wav and /dev/null differ diff --git a/audio_samples/12_ASR_IMDA_PART4_30_ASR_v2_103.wav b/audio_samples/12_ASR_IMDA_PART4_30_ASR_v2_103.wav deleted file mode 100644 index 186c8c090c344c63e0ea828cc12a51207df58aff..0000000000000000000000000000000000000000 Binary files a/audio_samples/12_ASR_IMDA_PART4_30_ASR_v2_103.wav and /dev/null differ diff --git a/audio_samples/13_ASR_IMDA_PART5_30_ASR_v2_1446.wav b/audio_samples/13_ASR_IMDA_PART5_30_ASR_v2_1446.wav deleted file mode 100644 index 0e606bfd770bb85abab4957d0380fef221c254c4..0000000000000000000000000000000000000000 Binary files a/audio_samples/13_ASR_IMDA_PART5_30_ASR_v2_1446.wav and /dev/null differ diff --git a/audio_samples/14_ASR_IMDA_PART5_30_ASR_v2_2281.wav b/audio_samples/14_ASR_IMDA_PART5_30_ASR_v2_2281.wav deleted file mode 100644 index cbf2fad1cc780f4a7d691974033dcef7fd0fcef0..0000000000000000000000000000000000000000 Binary files a/audio_samples/14_ASR_IMDA_PART5_30_ASR_v2_2281.wav and /dev/null differ diff --git a/audio_samples/15_ASR_IMDA_PART5_30_ASR_v2_4388.wav b/audio_samples/15_ASR_IMDA_PART5_30_ASR_v2_4388.wav deleted file mode 100644 index 8ea95dd7dbab7762154da8588b7ead701317e956..0000000000000000000000000000000000000000 Binary files a/audio_samples/15_ASR_IMDA_PART5_30_ASR_v2_4388.wav and /dev/null differ diff --git a/audio_samples/16_ASR_IMDA_PART6_30_ASR_v2_576.wav b/audio_samples/16_ASR_IMDA_PART6_30_ASR_v2_576.wav deleted file mode 100644 index df7b46f0a8f4f93b280cd9c91e486956e5d89b11..0000000000000000000000000000000000000000 Binary files a/audio_samples/16_ASR_IMDA_PART6_30_ASR_v2_576.wav and /dev/null differ diff --git a/audio_samples/17_ASR_IMDA_PART6_30_ASR_v2_1413.wav b/audio_samples/17_ASR_IMDA_PART6_30_ASR_v2_1413.wav deleted file mode 100644 index 69c2b3ee39465bc58efe769fde69c95c9d5092fc..0000000000000000000000000000000000000000 Binary files a/audio_samples/17_ASR_IMDA_PART6_30_ASR_v2_1413.wav and /dev/null differ diff --git a/audio_samples/18_ASR_IMDA_PART6_30_ASR_v2_2834.wav b/audio_samples/18_ASR_IMDA_PART6_30_ASR_v2_2834.wav deleted file mode 100644 index 1d89e648d87d2bc193f728ac86b54ea7a4e07634..0000000000000000000000000000000000000000 Binary files a/audio_samples/18_ASR_IMDA_PART6_30_ASR_v2_2834.wav and /dev/null differ diff --git a/audio_samples/19_ASR_AIShell_zh_ASR_v2_5044.wav b/audio_samples/19_ASR_AIShell_zh_ASR_v2_5044.wav deleted file mode 100644 index b296224725ec5acf74a02304f6beb6a7723d2c89..0000000000000000000000000000000000000000 Binary files a/audio_samples/19_ASR_AIShell_zh_ASR_v2_5044.wav and /dev/null differ diff --git a/audio_samples/1_ASR_IMDA_PART1_ASR_v2_141.wav b/audio_samples/1_ASR_IMDA_PART1_ASR_v2_141.wav deleted file mode 100644 index 17c5fc99647aaa658eabe035b40f97f8ea7638d1..0000000000000000000000000000000000000000 Binary files a/audio_samples/1_ASR_IMDA_PART1_ASR_v2_141.wav and /dev/null differ diff --git a/audio_samples/20_ASR_LIBRISPEECH_CLEAN_ASR_V2_833.wav b/audio_samples/20_ASR_LIBRISPEECH_CLEAN_ASR_V2_833.wav deleted file mode 100644 index 1ec609efd1c3790487c3c0aec77e5e3e5b0c3eda..0000000000000000000000000000000000000000 Binary files a/audio_samples/20_ASR_LIBRISPEECH_CLEAN_ASR_V2_833.wav and /dev/null differ diff --git a/audio_samples/25_ST_COVOST2_ZH-CN_EN_ST_V2_4567.wav b/audio_samples/25_ST_COVOST2_ZH-CN_EN_ST_V2_4567.wav deleted file mode 100644 index 55c435f3b228e136e3c1047a4b43e992b9acfc0f..0000000000000000000000000000000000000000 Binary files a/audio_samples/25_ST_COVOST2_ZH-CN_EN_ST_V2_4567.wav and /dev/null differ diff --git a/audio_samples/26_ST_COVOST2_EN_ZH-CN_ST_V2_5422.wav b/audio_samples/26_ST_COVOST2_EN_ZH-CN_ST_V2_5422.wav deleted file mode 100644 index f2780b3b7da1d553f59f4f29256b4e848049cf52..0000000000000000000000000000000000000000 Binary files a/audio_samples/26_ST_COVOST2_EN_ZH-CN_ST_V2_5422.wav and /dev/null differ diff --git a/audio_samples/27_ST_COVOST2_EN_ZH-CN_ST_V2_6697.wav b/audio_samples/27_ST_COVOST2_EN_ZH-CN_ST_V2_6697.wav deleted file mode 100644 index 234f811d4c60ab67659f06bcd1db481a11648ca9..0000000000000000000000000000000000000000 Binary files a/audio_samples/27_ST_COVOST2_EN_ZH-CN_ST_V2_6697.wav and /dev/null differ diff --git a/audio_samples/28_SI_ALPACA-GPT4-AUDIO_SI_V2_299.wav b/audio_samples/28_SI_ALPACA-GPT4-AUDIO_SI_V2_299.wav deleted file mode 100644 index 239fff4d4cfcf2653e00d97ca842f334bd31ed18..0000000000000000000000000000000000000000 Binary files a/audio_samples/28_SI_ALPACA-GPT4-AUDIO_SI_V2_299.wav and /dev/null differ diff --git a/audio_samples/29_SI_ALPACA-GPT4-AUDIO_SI_V2_750.wav b/audio_samples/29_SI_ALPACA-GPT4-AUDIO_SI_V2_750.wav deleted file mode 100644 index 35d9dfbdc9ca3169a05c50a548cb5836adc65d52..0000000000000000000000000000000000000000 Binary files a/audio_samples/29_SI_ALPACA-GPT4-AUDIO_SI_V2_750.wav and /dev/null differ diff --git a/audio_samples/2_ASR_IMDA_PART1_ASR_v2_2258.wav b/audio_samples/2_ASR_IMDA_PART1_ASR_v2_2258.wav deleted file mode 100644 index 1b3ff08f36d5e02043445bd8c0f37b73cdd9f59c..0000000000000000000000000000000000000000 Binary files a/audio_samples/2_ASR_IMDA_PART1_ASR_v2_2258.wav and /dev/null differ diff --git a/audio_samples/30_SI_ALPACA-GPT4-AUDIO_SI_V2_1454.wav b/audio_samples/30_SI_ALPACA-GPT4-AUDIO_SI_V2_1454.wav deleted file mode 100644 index d84f6abdca95d5bfa3f292f45b370c243bf79f86..0000000000000000000000000000000000000000 Binary files a/audio_samples/30_SI_ALPACA-GPT4-AUDIO_SI_V2_1454.wav and /dev/null differ diff --git a/audio_samples/31_SI_OPENHERMES-AUDIO_SI_V2_673.wav b/audio_samples/31_SI_OPENHERMES-AUDIO_SI_V2_673.wav deleted file mode 100644 index e0d9a7f61f0a8b0137bc8c5ddd4d03c02686b49b..0000000000000000000000000000000000000000 Binary files a/audio_samples/31_SI_OPENHERMES-AUDIO_SI_V2_673.wav and /dev/null differ diff --git a/audio_samples/32_SQA_CN_COLLEDGE_ENTRANCE_ENGLISH_TEST_SQA_V2_572.wav b/audio_samples/32_SQA_CN_COLLEDGE_ENTRANCE_ENGLISH_TEST_SQA_V2_572.wav deleted file mode 100644 index 4f0aadf1e9ac1e100c052fa9df0760651e2b2c4f..0000000000000000000000000000000000000000 Binary files a/audio_samples/32_SQA_CN_COLLEDGE_ENTRANCE_ENGLISH_TEST_SQA_V2_572.wav and /dev/null differ diff --git a/audio_samples/33_SQA_IMDA_PART3_30_SQA_V2_2310.wav b/audio_samples/33_SQA_IMDA_PART3_30_SQA_V2_2310.wav deleted file mode 100644 index c2858560478a1b51a6085e0f54a34d4bbca30b8e..0000000000000000000000000000000000000000 Binary files a/audio_samples/33_SQA_IMDA_PART3_30_SQA_V2_2310.wav and /dev/null differ diff --git a/audio_samples/34_SQA_IMDA_PART3_30_SQA_V2_3621.wav b/audio_samples/34_SQA_IMDA_PART3_30_SQA_V2_3621.wav deleted file mode 100644 index e4f53b20b6210ef6bba708ea1bccb9ad787caf22..0000000000000000000000000000000000000000 Binary files a/audio_samples/34_SQA_IMDA_PART3_30_SQA_V2_3621.wav and /dev/null differ diff --git a/audio_samples/35_SQA_IMDA_PART3_30_SQA_V2_4062.wav b/audio_samples/35_SQA_IMDA_PART3_30_SQA_V2_4062.wav deleted file mode 100644 index 8e18d39cdceaa84abc9dff3f002a0c6502c30b69..0000000000000000000000000000000000000000 Binary files a/audio_samples/35_SQA_IMDA_PART3_30_SQA_V2_4062.wav and /dev/null differ diff --git a/audio_samples/36_DS_IMDA_PART4_30_DS_V2_849.wav b/audio_samples/36_DS_IMDA_PART4_30_DS_V2_849.wav deleted file mode 100644 index 6b381a7b04f312f0b317bd3b6a0581155aeaf4c1..0000000000000000000000000000000000000000 Binary files a/audio_samples/36_DS_IMDA_PART4_30_DS_V2_849.wav and /dev/null differ diff --git a/audio_samples/39_Paralingual_IEMOCAP_ER_V2_91.wav b/audio_samples/39_Paralingual_IEMOCAP_ER_V2_91.wav deleted file mode 100644 index 738c14bf9ff890820659be0ad4d27ec5576ea7c4..0000000000000000000000000000000000000000 Binary files a/audio_samples/39_Paralingual_IEMOCAP_ER_V2_91.wav and /dev/null differ diff --git a/audio_samples/3_ASR_IMDA_PART1_ASR_v2_2265.wav b/audio_samples/3_ASR_IMDA_PART1_ASR_v2_2265.wav deleted file mode 100644 index 507bca925cbe5c433d1021c89f8f5c2108fc00d6..0000000000000000000000000000000000000000 Binary files a/audio_samples/3_ASR_IMDA_PART1_ASR_v2_2265.wav and /dev/null differ diff --git a/audio_samples/40_Paralingual_IEMOCAP_ER_V2_567.wav b/audio_samples/40_Paralingual_IEMOCAP_ER_V2_567.wav deleted file mode 100644 index 6709d5a7b3509690d89d222e8a75120b0a9c4d35..0000000000000000000000000000000000000000 Binary files a/audio_samples/40_Paralingual_IEMOCAP_ER_V2_567.wav and /dev/null differ diff --git a/audio_samples/42_Paralingual_IEMOCAP_GR_V2_320.wav b/audio_samples/42_Paralingual_IEMOCAP_GR_V2_320.wav deleted file mode 100644 index 593e18ad1ff04af7877072ba964c323786ba580e..0000000000000000000000000000000000000000 Binary files a/audio_samples/42_Paralingual_IEMOCAP_GR_V2_320.wav and /dev/null differ diff --git a/audio_samples/43_Paralingual_IEMOCAP_GR_V2_129.wav b/audio_samples/43_Paralingual_IEMOCAP_GR_V2_129.wav deleted file mode 100644 index cd143063c19ca28fb3820ded2f1caa2cda0a8861..0000000000000000000000000000000000000000 Binary files a/audio_samples/43_Paralingual_IEMOCAP_GR_V2_129.wav and /dev/null differ diff --git a/audio_samples/45_Paralingual_IMDA_PART3_30_GR_V2_12312.wav b/audio_samples/45_Paralingual_IMDA_PART3_30_GR_V2_12312.wav deleted file mode 100644 index af4fe23487085a3047ad1f0f56b824a6a75907f4..0000000000000000000000000000000000000000 Binary files a/audio_samples/45_Paralingual_IMDA_PART3_30_GR_V2_12312.wav and /dev/null differ diff --git a/audio_samples/47_Paralingual_IMDA_PART3_30_NR_V2_10479.wav b/audio_samples/47_Paralingual_IMDA_PART3_30_NR_V2_10479.wav deleted file mode 100644 index 20a685bb51cd1670280e104e1f06987e471657bb..0000000000000000000000000000000000000000 Binary files a/audio_samples/47_Paralingual_IMDA_PART3_30_NR_V2_10479.wav and /dev/null differ diff --git a/audio_samples/49_Paralingual_MELD_ER_V2_676.wav b/audio_samples/49_Paralingual_MELD_ER_V2_676.wav deleted file mode 100644 index a614033adb66d5d8b5a0054530336876c0d61d86..0000000000000000000000000000000000000000 Binary files a/audio_samples/49_Paralingual_MELD_ER_V2_676.wav and /dev/null differ diff --git a/audio_samples/4_ASR_IMDA_PART2_ASR_v2_999.wav b/audio_samples/4_ASR_IMDA_PART2_ASR_v2_999.wav deleted file mode 100644 index 48bfb135fc3eb12814801c49abd0b8250178ad86..0000000000000000000000000000000000000000 Binary files a/audio_samples/4_ASR_IMDA_PART2_ASR_v2_999.wav and /dev/null differ diff --git a/audio_samples/50_Paralingual_MELD_ER_V2_692.wav b/audio_samples/50_Paralingual_MELD_ER_V2_692.wav deleted file mode 100644 index 69f435f7308b5090f2668d22c1f324d30dd8857e..0000000000000000000000000000000000000000 Binary files a/audio_samples/50_Paralingual_MELD_ER_V2_692.wav and /dev/null differ diff --git a/audio_samples/51_Paralingual_VOXCELEB1_GR_V2_2148.wav b/audio_samples/51_Paralingual_VOXCELEB1_GR_V2_2148.wav deleted file mode 100644 index 42d4d89846cfcd0c6bb0de173f584ad2b6d6d131..0000000000000000000000000000000000000000 Binary files a/audio_samples/51_Paralingual_VOXCELEB1_GR_V2_2148.wav and /dev/null differ diff --git a/audio_samples/53_Paralingual_VOXCELEB1_NR_V2_2286.wav b/audio_samples/53_Paralingual_VOXCELEB1_NR_V2_2286.wav deleted file mode 100644 index ce05d92f8004d6054d39fae59f4d3a34c3b80e49..0000000000000000000000000000000000000000 Binary files a/audio_samples/53_Paralingual_VOXCELEB1_NR_V2_2286.wav and /dev/null differ diff --git a/audio_samples/55_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_2.wav b/audio_samples/55_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_2.wav deleted file mode 100644 index f8513f46825e7b386b1f00f058d249044dac82d2..0000000000000000000000000000000000000000 Binary files a/audio_samples/55_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_2.wav and /dev/null differ diff --git a/audio_samples/56_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_415.wav b/audio_samples/56_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_415.wav deleted file mode 100644 index f95f167ebe177b0db82f346f9dbd2c51eb828ec1..0000000000000000000000000000000000000000 Binary files a/audio_samples/56_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_415.wav and /dev/null differ diff --git a/audio_samples/57_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_460.wav b/audio_samples/57_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_460.wav deleted file mode 100644 index c2decc6d21300257c3fc74b6718f1898dedbf4e2..0000000000000000000000000000000000000000 Binary files a/audio_samples/57_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_460.wav and /dev/null differ diff --git a/audio_samples/5_ASR_IMDA_PART2_ASR_v2_2241.wav b/audio_samples/5_ASR_IMDA_PART2_ASR_v2_2241.wav deleted file mode 100644 index 55063388c14bd69df6a8023e5a65e4c9c3a01fb5..0000000000000000000000000000000000000000 Binary files a/audio_samples/5_ASR_IMDA_PART2_ASR_v2_2241.wav and /dev/null differ diff --git a/audio_samples/6_ASR_IMDA_PART2_ASR_v2_3409.wav b/audio_samples/6_ASR_IMDA_PART2_ASR_v2_3409.wav deleted file mode 100644 index daf99a1877bae21a5ab72147a7a6359c8953e242..0000000000000000000000000000000000000000 Binary files a/audio_samples/6_ASR_IMDA_PART2_ASR_v2_3409.wav and /dev/null differ diff --git a/audio_samples/7_ASR_IMDA_PART3_30_ASR_v2_2269.wav b/audio_samples/7_ASR_IMDA_PART3_30_ASR_v2_2269.wav deleted file mode 100644 index 5e439cf43817a436692e132e194bcf2b43332126..0000000000000000000000000000000000000000 Binary files a/audio_samples/7_ASR_IMDA_PART3_30_ASR_v2_2269.wav and /dev/null differ diff --git a/audio_samples/8_ASR_IMDA_PART3_30_ASR_v2_1698.wav b/audio_samples/8_ASR_IMDA_PART3_30_ASR_v2_1698.wav deleted file mode 100644 index e0929f09849acb481f80ca007bf257a9d937c035..0000000000000000000000000000000000000000 Binary files a/audio_samples/8_ASR_IMDA_PART3_30_ASR_v2_1698.wav and /dev/null differ diff --git a/audio_samples/9_ASR_IMDA_PART3_30_ASR_v2_2474.wav b/audio_samples/9_ASR_IMDA_PART3_30_ASR_v2_2474.wav deleted file mode 100644 index 11e66f37907da37aa2d90a492e407bc3a7a20bb1..0000000000000000000000000000000000000000 Binary files a/audio_samples/9_ASR_IMDA_PART3_30_ASR_v2_2474.wav and /dev/null differ diff --git a/audio_samples/female_pilot.wav b/audio_samples/female_pilot.wav deleted file mode 100644 index 8492f4dcff3ae93e641d10bdf2cba8a3290bda4c..0000000000000000000000000000000000000000 --- a/audio_samples/female_pilot.wav +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a881f64b78e959491e5a0731e41acdb513fc8a91cf817c3f1da6776d1cfa0245 -size 5664058 diff --git a/audio_samples/song_1.wav b/audio_samples/song_1.wav deleted file mode 100644 index 5a40bbc94858189c9252921e9ee11157e3821bd2..0000000000000000000000000000000000000000 --- a/audio_samples/song_1.wav +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:303fc4a3003e2f49cfcfd1c5f7f79fed09ec50b67a0f96838a20c39d306538f7 -size 11420470 diff --git a/index.html b/index.html new file mode 100644 index 0000000000000000000000000000000000000000..2a7abb44a7abcb287ac148f1a0db1d73841bc4ba --- /dev/null +++ b/index.html @@ -0,0 +1,8 @@ + + +
This {component_name.lower()} is based on - MERaLiON-AudioLLM, - developed by I2R, A*STAR, in collaboration with AISG, Singapore. - {description}
This {component_name.lower()} is based on - MERaLiON-AudioLLM.{concise_description}