update

examples/badcase_filter/bad_case_find.py

@@ -1,54 +0,0 @@
-#!/usr/bin/python3
-# -*- coding: utf-8 -*-
-import argparse
-import json
-from pathlib import Path
-import shutil
-
-from gradio_client import Client, handle_file
-from tqdm import tqdm
-
-from project_settings import project_path
-
-
-def get_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "--data_dir",
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\audio_lib_hkg_12\es-MX2",
-        # default=(project_path / "data/calling/62/wav_segmented"),
-        type=str
-    )
-    args = parser.parse_args()
-    return args
-
-
-def main():
-    args = get_args()
-
-    data_dir = Path(args.data_dir)
-
-    client = Client("http://127.0.0.1:7864/")
-
-    for idx, filename in tqdm(enumerate(data_dir.glob("**/active_media_r_*.wav"))):
-        filename = filename.as_posix()
-
-        sub_audio_dataset = client.predict(
-            audio_t=handle_file(filename),
-            model_name="sound-2-ch16-cnn",
-            label="voice",
-            win_size=2,
-            win_step=0.25,
-            n_erode=2,
-            n_dilate=2,
-            api_name="/when_click_split_button"
-        )
-        sub_audio_dataset = sub_audio_dataset["samples"]
-        if len(sub_audio_dataset) == 0:
-            continue
-
-    return
-
-
-if __name__ == "__main__":
-    main()

examples/download_wav/Temp Query 5_20251008-093912.csv

@@ -1,101 +0,0 @@
-date,overdue_term,id,case_id,credit_user_id,call_start_timestamp,call_end_timestamp,thirdpart_download_url
-11/10/2025,M3,201577107,62145483,2.05158E+18,1760156453,1760156464,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/6b76d306-b767-44e5-be9a-0a15d1165113.mp3
-11/10/2025,M3,201552895,61647547,2.04871E+18,1760150223,1760150235,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/91eb4d93-aaaf-4a22-b1b5-93f90790f360.mp3
-11/10/2025,M1,201571248,64869969,1.63814E+18,1760154872,1760154878,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/9feab432-a05f-4c12-a7a5-1de81c5c5552.mp3
-10/10/2025,M5,201481243,57774660,1.86995E+18,1760093720,1760093736,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/8ca27707-73e9-41a9-a531-f84011a2d021.mp3
-11/10/2025,M6,201602065,56556981,1.96434E+18,1760162403,1760162411,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/23edb55b-d7d7-496d-92d9-27be9a8d0f06.mp3
-10/10/2025,M3,201432876,62937736,1.71926E+18,1760081217,1760081223,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/d64b9511-1ada-435c-bf1d-7ff8edd194d1.mp3
-10/10/2025,M2,201418064,63818662,2.06059E+18,1760078017,1760078023,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/7a53b0cf-d4a8-496b-8533-578e1b3c8050.mp3
-11/10/2025,M1,201546922,65604125,1.86304E+18,1760149167,1760149175,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/e6adf4e4-269c-4668-955d-7b3dd1c60736.mp3
-10/10/2025,M3,201430098,61807602,1.85118E+18,1760080774,1760080785,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/b2b8e1e5-d92d-424d-9150-7af7506305c4.mp3
-10/10/2025,M1,201448566,64796208,1.65278E+18,1760085408,1760085415,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/09d6248c-111d-4b73-910f-e218049185d8.mp3
-11/10/2025,M4,201571566,60538522,1.88122E+18,1760154923,1760154930,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/944211c2-e492-4889-b655-e508fdd5879d.mp3
-11/10/2025,M1,201566967,65843234,2.02107E+18,1760154065,1760154073,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/bfa8591b-e527-45e9-ae57-7f74f9e7302b.mp3
-10/10/2025,M2,201447321,64267309,1.56498E+18,1760085020,1760085033,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/4bb8e69a-4c6c-4828-857a-ce0e43cc75a1.mp3
-11/10/2025,M1,201568415,65114574,4883832,1760154398,1760154405,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/51e805c9-5cc5-490b-bae2-7d5eab6f343c.mp3
-11/10/2025,M2,201605984,63943082,1.8374E+18,1760163009,1760163030,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/98af45d4-16cd-4eaf-9b91-05c7143a26bc.mp3
-10/10/2025,M1,201419656,66515322,1.49814E+17,1760078339,1760078345,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/91f43558-6567-43d9-a709-ffa3173c81b4.mp3
-10/10/2025,M2,201427406,63880041,1.56918E+18,1760080267,1760080275,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/375fdc20-428e-4658-aeb7-cb9cca17c534.mp3
-11/10/2025,M1,201575782,64887894,1.73042E+18,1760156066,1760156082,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/b2d6b5a2-3d7f-4fc7-abf6-258cd7a7de5f.mp3
-10/10/2025,M3,201418794,62368390,1.94558E+18,1760078142,1760078156,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/ba673b33-8496-4901-8f2f-8083802a5213.mp3
-10/10/2025,M1,201424572,66395236,1203507,1760079797,1760079804,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/a95596c0-8b46-4333-b126-6c4c11ca41fc.mp3
-11/10/2025,M2,201571228,64248917,1.88019E+18,1760154871,1760154880,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/e4eb3384-2d75-4563-b9a7-7bb3256a2aae.mp3
-11/10/2025,M4,201570642,60447265,1.98507E+18,1760154782,1760154787,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/a5440c2e-3fc5-43b2-8ecf-d4bde44f62e8.mp3
-10/10/2025,M5,201453357,58652419,1.85737E+18,1760086342,1760086350,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/68def6c9-130e-4705-b4b6-19d5d8b4b27d.mp3
-11/10/2025,M6,201573623,57234397,1.97251E+18,1760155303,1760155313,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/0ba67a44-c94a-4d68-a6ba-d003cf4b57c8.mp3
-10/10/2025,M5,201424683,57553385,1.86241E+18,1760079814,1760079831,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/50c26933-40a1-45bc-baf0-eb7b4c268ffb.mp3
-11/10/2025,M1,201570171,66334366,1.8276E+18,1760154717,1760154723,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/ecbb5b43-19cf-44e2-8ee4-ea131c706421.mp3
-10/10/2025,M4,201451276,59840709,2.04014E+18,1760085947,1760085952,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/6059e9c2-2f3c-4cef-a536-4796436b9765.mp3
-10/10/2025,M4,201432508,59867441,1.91396E+18,1760081156,1760081172,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/c0814466-4e13-4ef1-b4be-2fbe66eebfd8.mp3
-11/10/2025,M5,201612109,58418373,1.87946E+18,1760163975,1760163983,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/c7c54616-575a-4dc9-9820-fea245211933.mp3
-10/10/2025,M2,201432653,64650851,1.74295E+18,1760081176,1760081192,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/e8cc82f1-ded6-484f-9e6a-b9bf514eda04.mp3
-11/10/2025,M1,201580231,65755142,1.96545E+18,1760157408,1760157415,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/d2ed8a99-d8a4-4c0a-9b30-0a4f97e8db6e.mp3
-10/10/2025,M3,201430023,61812734,7400607,1760080766,1760080780,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/f693b1d5-dc99-43d9-a730-2040ca645f17.mp3
-10/10/2025,M3,201450322,62009884,2.007E+18,1760085762,1760085768,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/4915b87b-1169-41f7-af8c-6509a66dfbe6.mp3
-10/10/2025,M3,201431281,62172812,2.05076E+18,1760080963,1760080975,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/dc9c5331-04bb-4cbf-b789-61b0b811d6b6.mp3
-10/10/2025,M5,201430080,58314791,1.99801E+18,1760080772,1760080777,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/e571b6f4-6471-4311-81ed-cd1af7e55e07.mp3
-11/10/2025,M4,201538284,59471661,2.03412E+18,1760147632,1760147638,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/cfbe5f77-02b3-4a04-8948-9ca4237c3abc.mp3
-10/10/2025,M1,201447219,65817559,2.02777E+18,1760085001,1760085007,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/49dad1dd-d681-410a-87df-649eca036ff0.mp3
-10/10/2025,M1,201481818,66043196,1.93698E+18,1760093888,1760093894,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/93c19c1f-93fa-41ec-8f57-54a606a7f4a4.mp3
-10/10/2025,M1,201485519,66563695,2.074E+18,1760095020,1760095034,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/e8c214bd-6261-42a7-863b-3bcbd82f081e.mp3
-11/10/2025,M5,201595914,59014301,1.5286E+18,1760161399,1760161415,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/095bcf3f-1807-4c71-a997-ce6806b4da99.mp3
-11/10/2025,M2,201533318,63403949,1.88317E+18,1760146862,1760146871,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/8ae1702d-eca8-4e77-b39d-fd119c72499e.mp3
-11/10/2025,M4,201576553,60295505,1.80115E+18,1760156314,1760156320,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/47bad51d-65fb-4795-9211-a8a0434b95ad.mp3
-10/10/2025,M1,201485741,65280144,2.07517E+18,1760095107,1760095114,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/87d8ccb1-f7e9-4377-a1d8-7bf9228e0c3f.mp3
-10/10/2025,M1,201431349,64854591,1.58546E+18,1760080970,1760080978,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/6f983610-0fd3-4da6-be49-1cc50f205618.mp3
-10/10/2025,M5,201487648,57318618,1.64505E+18,1760095790,1760095797,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/254f796e-b955-4a5e-a190-1d3579474645.mp3
-11/10/2025,M1,201577796,64963614,1.86777E+18,1760156648,1760156657,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/b382a477-933e-43b1-8759-a2b4e17e92b2.mp3
-11/10/2025,M3,201533254,62192769,2.023E+18,1760146812,1760146817,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/ac78c5f9-7109-45fc-87da-5e275e0159f4.mp3
-10/10/2025,M1,201428974,65690748,1.89974E+18,1760080550,1760080557,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/b4e53f33-4c55-4b16-b786-6619332f47fc.mp3
-11/10/2025,M2,201546294,64684883,1.93667E+18,1760149074,1760149090,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/337edca5-80fa-4f9d-8820-3fb333b384d5.mp3
-10/10/2025,M1,201475668,66214001,1.80957E+18,1760092690,1760092695,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/21e2b2ec-2475-4692-9b67-2453e262e77b.mp3
-10/10/2025,M5,201459599,57741938,6633631,1760087612,1760087617,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/02bd6e79-efc1-4cfd-bee9-12967c844735.mp3
-11/10/2025,M3,201551060,61444707,1.94443E+18,1760149891,1760149899,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/700c2e32-c5bd-48f3-8085-0617694963dd.mp3
-10/10/2025,M4,201453055,59345041,1.68365E+18,1760086275,1760086282,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/4f1ef95b-3432-41d3-8970-1698504ba010.mp3
-10/10/2025,M1,201426891,66520128,1728931,1760080190,1760080196,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/ec7180ac-2948-49a3-b709-f60b80dfee27.mp3
-12/10/2025,M1,201704571,66237684,1.77477E+18,1760229906,1760229911,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251012/21962/b70ed0f3-145f-49a6-9dbb-aa695e21d7de.mp3
-10/10/2025,M1,201457899,65109188,1.58483E+18,1760087330,1760087339,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/c5f910f6-6a5e-4bd0-8a64-f2805837558d.mp3
-11/10/2025,M2,201537965,63920995,2.04332E+18,1760147578,1760147593,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/38ff4d8b-4db3-4410-902e-3953699bf4eb.mp3
-11/10/2025,M1,201568081,66644507,1.92267E+18,1760154313,1760154318,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/a801cfcc-40d2-4dde-9994-b709836df856.mp3
-11/10/2025,M3,201539641,62112487,1.75162E+18,1760147868,1760147875,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/56ec2c07-3bf5-47ba-82c6-039bf094d6ca.mp3
-10/10/2025,M1,201483514,65958944,1.96386E+18,1760094328,1760094335,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/edd080b5-2439-4079-a27f-2f0941217825.mp3
-10/10/2025,M5,201417598,57494166,1.59238E+18,1760077922,1760077928,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/65750a23-6edc-479a-bea4-14ba9e43648e.mp3
-11/10/2025,M1,201528466,65224705,1.75014E+18,1760145272,1760145278,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/5b63572f-79d2-4d22-9ded-4fa2e3cd372b.mp3
-10/10/2025,M5,201453641,58921447,1.92301E+18,1760086392,1760086405,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/4a9b93d4-9878-4023-8dd2-40fcf9502a49.mp3
-11/10/2025,M1,201611955,65789335,1.88401E+18,1760163939,1760163946,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/6fb4f49d-fe9c-4a64-8c74-b5649d7e8175.mp3
-10/10/2025,M1,201459093,66318002,1.61088E+18,1760087527,1760087538,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/8a608622-e3d7-4a96-89ac-1300b7653c6f.mp3
-10/10/2025,M2,201418416,63100145,1.85044E+18,1760078077,1760078083,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/f6ab0a88-2055-4b88-9fbd-7af4aef5731f.mp3
-11/10/2025,M3,201537163,61356706,2.04189E+18,1760147448,1760147453,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/f1f6ad6a-7399-4fb2-8073-c83ef7093b6e.mp3
-10/10/2025,M3,201480897,61752670,1.99088E+18,1760093653,1760093662,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/cdf7552c-a3a8-4cfc-a4b1-651f84141090.mp3
-11/10/2025,M2,201605821,63901708,2.06357E+18,1760162987,1760162993,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/70b3816a-2e43-403a-97e0-dd3288596c71.mp3
-10/10/2025,M3,201457652,61356706,2.04189E+18,1760087292,1760087299,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/d5f5598a-b93c-4fb8-8bb1-56acc9bb0033.mp3
-10/10/2025,M2,201480118,64077815,1.99009E+18,1760093518,1760093526,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/8cac232e-2ed4-4506-8bcf-2a8e4bca91b5.mp3
-11/10/2025,M1,201551882,65617862,1.65598E+18,1760150016,1760150024,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/e71c8472-c3f7-486e-a388-1196836899bf.mp3
-10/10/2025,M5,201417451,58993884,1.18898E+16,1760077893,1760077905,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/2965b989-cf94-4dc4-afaa-5fda4ac4bb34.mp3
-11/10/2025,M5,201547506,58539902,1.92196E+18,1760149254,1760149265,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/1cb5b911-69c9-4b5a-ab2f-e4bad61dd0be.mp3
-11/10/2025,M1,201606566,66579640,1.92316E+18,1760163098,1760163103,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/2e5ff340-8197-4069-8533-0d47a221dc57.mp3
-11/10/2025,M2,201545849,63976411,2.01076E+18,1760148993,1760148999,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/e7592b1f-d24d-4fb5-afb9-0d64f23719d5.mp3
-10/10/2025,M1,201487535,66304049,1.96729E+18,1760095749,1760095754,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/03b31201-d6f7-4246-80ef-ec902f93e6bf.mp3
-10/10/2025,M1,201458971,66590224,2.06508E+18,1760087508,1760087515,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/01013ca6-1659-4613-8ae7-5d79372d4464.mp3
-11/10/2025,M4,201548032,59720355,1.54183E+18,1760149338,1760149343,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/61bafa17-b411-4d1a-b9bd-1a76c5087b9e.mp3
-10/10/2025,M5,201430001,57789932,1.99701E+18,1760080762,1760080768,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/aa25ffd1-82a2-4048-938d-0adc335cec41.mp3
-11/10/2025,M1,201596095,66001014,1.94845E+18,1760161430,1760161436,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/76c67081-af66-4a80-b531-25b14a8e0443.mp3
-11/10/2025,M3,201549933,62873165,1.87383E+18,1760149739,1760149747,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/fd0caad7-72fd-4152-a8ed-58253e946567.mp3
-10/10/2025,M5,201447596,58417708,1.9626E+18,1760085087,1760085092,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/0f8f64c4-2587-4501-abb8-23e0e5389635.mp3
-11/10/2025,M1,201596157,65991243,1.88004E+18,1760161446,1760161452,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/8f731992-cbc6-45e1-8203-5628d51a6e45.mp3
-10/10/2025,M2,201391828,63462209,1.1835E+16,1760067513,1760067535,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/2c641568-ebf6-4989-abeb-e2bc404d79e8.mp3
-11/10/2025,M4,201579066,60241526,1.95443E+18,1760157061,1760157070,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/34c79266-7c59-4e26-b936-05d64716fa79.mp3
-11/10/2025,M3,201539123,61552513,1.65655E+18,1760147755,1760147762,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/1dc2d33a-f080-4cb4-ad66-fb50761b500a.mp3
-11/10/2025,M5,201607636,57899370,1.93241E+18,1760163267,1760163287,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/d8e13804-692a-4cf7-b4e2-781384a1d559.mp3
-10/10/2025,M4,201426209,60181850,1.79511E+18,1760080075,1760080081,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/8f81c559-7392-46ff-8ebb-1a6edc41381c.mp3
-11/10/2025,M1,201535197,66655594,1.66159E+18,1760147133,1760147139,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/d793a0e3-bd7b-44f3-a1e2-bc1eb0908c1a.mp3
-11/10/2025,M4,201613127,61191667,1.78852E+18,1760164234,1760164240,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/4e794fb2-01bf-41ff-843f-945b2b1ec9df.mp3
-10/10/2025,M3,201456582,61353852,1.70556E+18,1760087088,1760087093,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/5fe67f28-5f86-43bb-a87f-589b75118d56.mp3
-11/10/2025,M2,201536974,63373730,2.02636E+18,1760147420,1760147433,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/cf2bf8cc-e2af-478a-96e4-686c59a98d4d.mp3
-11/10/2025,M6,201598303,57270639,1.57805E+18,1760161833,1760161850,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/07e2de01-8040-4942-8586-77d6eb38b64f.mp3
-11/10/2025,M4,201577614,60545450,1.95248E+18,1760156607,1760156635,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/53f6d6eb-c22e-4935-9d3c-941969a0241f.mp3
-10/10/2025,M1,201451460,66451819,1406890,1760085972,1760085978,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251010/21962/43061915-f8e0-405b-9be0-bd3826d0aa69.mp3
-11/10/2025,M5,201566778,57480954,1.79569E+18,1760154035,1760154041,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/f737520a-d62f-4c71-a81c-bfbcbd2887d3.mp3
-11/10/2025,M5,201579474,58000396,1.17763E+16,1760157205,1760157215,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/b8d5a9b1-13cf-4667-8271-1b562de5dd22.mp3
-11/10/2025,M1,201547564,66391023,987018,1760149263,1760149269,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/434cea47-98a9-4f24-b29e-bee36e9f9832.mp3
-11/10/2025,M5,201538978,57340689,1.62497E+18,1760147736,1760147755,https://idn1.obs.ap-southeast-4.myhuaweicloud.com/20251011/21962/a74e253e-34cf-42df-9c3c-c8f6a45b994e.mp3

examples/download_wav/step_1_download_wav.py

@@ -31,7 +31,7 @@ def get_args():
     )
     parser.add_argument(
         "--output_dir",
-        default=(project_path / "data/calling/62/wav_2ch").as_posix(),
+        default=(project_path / "data/calling/63/wav_2ch").as_posix(),
         type=str
     )
     args = parser.parse_args()
@@ -39,7 +39,8 @@ def get_args():
 
 
 excel_file_str = """
-wiz_mv_samples_20251023-101746.csv
+record_1110.csv
+record_1104.csv
 """
 
 
@@ -75,8 +76,9 @@ def main():
         df = pd.read_csv(excel_file.as_posix())
         for i, row in tqdm(df.iterrows()):
             call_date = "2025-10-12 00:00:00"
-            record_url = row["thirdpart_download_url"]
+            record_url = row["record_file"]
             call_id = Path(record_url).stem
+            record_name = Path(record_url).name
 
             # call_date = row["Attempt time"]
             # call_id = row["Call ID"]
@@ -112,7 +114,7 @@ def main():
             if resp.status_code != 200:
                 raise AssertionError("status_code: {}; text: {}".format(resp.status_code, resp.text))
 
-            filename = output_dir / "{}.mp3".format(call_id)
+            filename = output_dir / f"{record_name}"
             with open(filename.as_posix(), "wb") as f:
                 f.write(resp.content)
 

examples/download_wav/step_2_to_1ch.py

@@ -17,12 +17,12 @@ def get_args():
 
     parser.add_argument(
         "--audio_dir",
-        default=(project_path / "data/calling/62/wav_2ch").as_posix(),
+        default=(project_path / "data/calling/63/wav_2ch").as_posix(),
         type=str
     )
     parser.add_argument(
         "--output_dir",
-        default=(project_path / "data/calling/62/wav_1ch").as_posix(),
+        default=(project_path / "data/calling/63/wav_1ch").as_posix(),
         type=str
     )
     args = parser.parse_args()
@@ -37,13 +37,13 @@ def main():
     output_dir.mkdir(parents=True, exist_ok=True)
 
     finished = set()
-    for filename in tqdm(list(output_dir.glob("*.mp3"))):
+    for filename in tqdm(list(output_dir.glob("*.wav"))):
         splits = filename.stem.split("_")
         call_id = splits[3]
         finished.add(call_id)
     print(f"finished count: {len(finished)}")
 
-    for filename in tqdm(list(audio_dir.glob("*.mp3"))):
+    for filename in tqdm(list(audio_dir.glob("*.wav"))):
         call_id = filename.stem
 
         if call_id in finished:
@@ -64,7 +64,7 @@ def main():
         # signal = signal[:, 0]
         signal = signal[0, :]
 
-        to_filename = output_dir / f"active_media_r_{call_id}_id-ID_none.wav"
+        to_filename = output_dir / f"active_media_r_{call_id}_en-PH_none.wav"
         try:
             wavfile.write(
                 to_filename.as_posix(),

examples/download_wav/step_3_split_two_second_wav.py

@@ -15,16 +15,16 @@ def get_args():
 
     parser.add_argument(
         "--audio_dir",
-        # default=(project_path / "data/calling/62/wav_1ch").as_posix(),
+        default=(project_path / "data/calling/63/wav_1ch").as_posix(),
         # default=(project_path / "data/calling/358/wav_1ch/finished/voicemail_annotation").as_posix(),
         # default=(project_path / "data/calling/358/wav_1ch/finished/voicemail_annotation").as_posix(),
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\audio_lib_hkg_1\es-MX\keep",
+        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\audio_lib_hkg_1\es-MX\keep",
         type=str
     )
     parser.add_argument(
         "--output_dir",
-        # default=(project_path / "data/calling/62/wav_segmented").as_posix(),
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup",
+        default=(project_path / "data/calling/63/wav_segmented").as_posix(),
+        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup",
         type=str
     )
     parser.add_argument(

examples/sample_filter/bad_case_find.py

@@ -15,30 +15,30 @@ def get_args():
     parser = argparse.ArgumentParser()
     parser.add_argument(
         "--data_dir",
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup",
-        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\backup",
-        # default=(project_path / "data/calling/62/wav_segmented"),
+        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup",
+        default=r"D:\Users\tianx\HuggingSpaces\wav_segmented",
+        # default=(project_path / "data/calling/63/wav_segmented"),
         type=str
     )
     parser.add_argument(
         "--keep_dir1",
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup\keep1",
-        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\backup\keep1",
-        # default=(project_path / "data/calling/62/wav_segmented/keep"),
+        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup\keep1",
+        default=r"D:\Users\tianx\HuggingSpaces\wav_segmented\keep1",
+        # default=(project_path / "data/calling/63/wav_segmented/keep1"),
         type=str
     )
     parser.add_argument(
         "--keep_dir2",
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup\keep2",
-        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\backup\keep2",
-        # default=(project_path / "data/calling/62/wav_segmented/keep"),
+        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup\keep2",
+        default=r"D:\Users\tianx\HuggingSpaces\wav_segmented\keep2",
+        # default=(project_path / "data/calling/63/wav_segmented/keep2"),
         type=str
     )
     parser.add_argument(
         "--trash_dir",
-        default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup\trash",
-        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\backup\trash",
-        # default=(project_path / "data/calling/62/wav_segmented/trash"),
+        # default=r"D:\Users\tianx\HuggingDatasets\international_voice\data\sea-idn\audio_lib_hkg_1\es-MX-backup\trash",
+        default=r"D:\Users\tianx\HuggingSpaces\wav_segmented\trash",
+        # default=(project_path / "data/calling/63/wav_segmented/trash"),
         type=str
     )
     args = parser.parse_args()
@@ -66,7 +66,7 @@ def main():
 
         outputs1 = client.predict(
             audio_t=handle_file(filename),
-            model_name="voicemail-es-mx-2-ch4-cnn",
+            model_name="voicemail-en-ph-2-ch4-cnn",
             ground_true="Hello!!",
             api_name="/when_click_cls_button"
         )
@@ -94,11 +94,6 @@ def main():
                 filename,
                 trash_dir.as_posix(),
             )
-        elif label2 in ("mute", "white_noise"):
-            shutil.move(
-                filename,
-                trash_dir.as_posix(),
-            )
         else:
             if label1 == "non_voicemail" and label2 in ("voice",):
                 tgt_dir = keep_dir1

examples/sample_filter/non_voicemail_filter.py

@@ -44,6 +44,8 @@ def main():
     client = Client("http://127.0.0.1:7864/")
 
     for idx, filename in tqdm(enumerate(data_dir.glob("active_media_r_*.wav"))):
+        if idx < 1600:
+            continue
         filename = filename.as_posix()
 
         model_name = f"voicemail-es-mx-2-ch4-cnn"

examples/sound_classification_by_cnn/run_batch.sh

@@ -99,10 +99,10 @@
 #--config_file "yaml/conv2d-classifier-4-ch32.yaml"
 
 
-sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name sound-8-ch32-cnn \
---filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" \
---label_plan 8 \
---config_file "yaml/conv2d-classifier-8-ch32.yaml"
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name sound-8-ch32-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" \
+#--label_plan 8 \
+#--config_file "yaml/conv2d-classifier-8-ch32.yaml"
 
 
 # pretrained voicemail
@@ -112,6 +112,16 @@ sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name fi
 --label_plan 2-voicemail \
 --config_file "yaml/conv2d-classifier-2-ch4.yaml"
 
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-2-ch8-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" \
+#--label_plan 2-voicemail \
+#--config_file "yaml/conv2d-classifier-2-ch8.yaml"
+#
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-2-ch16-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" \
+#--label_plan 2-voicemail \
+#--config_file "yaml/conv2d-classifier-2-ch16.yaml"
+
 sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-2-ch32-cnn \
 --filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" \
 --label_plan 2-voicemail \
@@ -120,12 +130,12 @@ sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name fi
 
 # voicemail ch4
 
-#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-en-ph-2-ch4-cnn \
-#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/en-PH/wav_finished/*/*.wav" \
-#--label_plan 2-voicemail \
-#--config_file "yaml/conv2d-classifier-2-ch4.yaml" \
-#--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch4-cnn.zip"
-#
+sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-en-ph-2-ch4-cnn \
+--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/en-PH/wav_finished/*/*.wav" \
+--label_plan 2-voicemail \
+--config_file "yaml/conv2d-classifier-2-ch4.yaml" \
+--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch4-cnn.zip"
+
 #sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-en-sg-2-ch4-cnn \
 #--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/en-SG/wav_finished/*/*.wav" \
 #--label_plan 2-voicemail \
@@ -138,11 +148,11 @@ sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name fi
 #--config_file "yaml/conv2d-classifier-2-ch4.yaml" \
 #--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch4-cnn.zip"
 
-sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-mx-2-ch4-cnn \
---filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-MX/wav_finished/*/*.wav" \
---label_plan 2-voicemail \
---config_file "yaml/conv2d-classifier-2-ch4.yaml" \
---pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch4-cnn.zip"
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-mx-2-ch4-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-MX/wav_finished/*/*.wav" \
+#--label_plan 2-voicemail \
+#--config_file "yaml/conv2d-classifier-2-ch4.yaml" \
+#--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch4-cnn.zip"
 
 #sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-pe-2-ch4-cnn \
 #--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-PE/wav_finished/*/*.wav" \
@@ -199,14 +209,35 @@ sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name fi
 #--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch4-cnn.zip"
 
 
-# voicemail ch32
 
-#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-en-ph-2-ch32-cnn \
-#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/en-PH/wav_finished/*/*.wav" \
+# voicemail ch8
+
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-mx-2-ch8-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-MX/wav_finished/*/*.wav" \
 #--label_plan 2-voicemail \
-#--config_file "yaml/conv2d-classifier-2-ch32.yaml" \
-#--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch32-cnn.zip"
+#--config_file "yaml/conv2d-classifier-2-ch8.yaml" \
+#--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch8-cnn.zip"
+
+
+
+# voicemail ch16
+
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-mx-2-ch16-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-MX/wav_finished/*/*.wav" \
+#--label_plan 2-voicemail \
+#--config_file "yaml/conv2d-classifier-2-ch16.yaml" \
+#--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch16-cnn.zip"
 #
+
+
+# voicemail ch32
+
+sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-en-ph-2-ch32-cnn \
+--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/en-PH/wav_finished/*/*.wav" \
+--label_plan 2-voicemail \
+--config_file "yaml/conv2d-classifier-2-ch32.yaml" \
+--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch32-cnn.zip"
+
 #sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-en-sg-2-ch32-cnn \
 #--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/en-SG/wav_finished/*/*.wav" \
 #--label_plan 2-voicemail \
@@ -219,11 +250,11 @@ sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name fi
 #--config_file "yaml/conv2d-classifier-2-ch32.yaml" \
 #--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch32-cnn.zip"
 
-sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-mx-2-ch32-cnn \
---filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-MX/wav_finished/*/*.wav" \
---label_plan 2-voicemail \
---config_file "yaml/conv2d-classifier-2-ch32.yaml" \
---pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch32-cnn.zip"
+#sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-mx-2-ch32-cnn \
+#--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-MX/wav_finished/*/*.wav" \
+#--label_plan 2-voicemail \
+#--config_file "yaml/conv2d-classifier-2-ch32.yaml" \
+#--pretrained_model "/data/tianxing/PycharmProjects/cc_audio_8/trained_models/voicemail-2-ch32-cnn.zip"
 
 #sh run.sh --stage 0 --stop_stage 6 --system_version centos --file_folder_name file_dir --final_model_name voicemail-es-pe-2-ch32-cnn \
 #--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/es-PE/wav_finished/*/*.wav" \

main.py

@@ -34,6 +34,8 @@ from huggingface_hub import snapshot_download
 import numpy as np
 import torch
 
+torch.set_num_threads(1)
+
 from project_settings import environment, project_path
 from toolbox.torch.utils.data.vocabulary import Vocabulary
 from tabs.cls_tab import get_cls_tab