Add UniverSLU model

add_tokens-Copy1.txt

@@ -0,0 +1 @@
+<|audio|>

exp/asr_train_asr_whisper_full_correct_specaug_target_raw_en_whisper_multilingual/RESULTS.md

@@ -0,0 +1,99 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Nov 30 23:16:47 CST 2023`
+- python version: `3.9.13 (main, Aug 25 2022, 23:26:10)  [GCC 11.2.0]`
+- espnet version: `espnet 202211`
+- pytorch version: `pytorch 1.12.1+cu116`
+- Git hash: `96e6eb97bacb428d9979661725657b5c38a17dee`
+  - Commit date: `Thu Mar 18 05:23:39 2021 +0000`
+
+## asr_train_asr_whisper_full_correct_specaug_target_raw_en_whisper_multilingual
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_acc_asr_model_valid.acc.ave/test_accentdb|3463|3463|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_acc_asr_model_valid.acc.ave_10best/test_accentdb|3463|3463|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_ar_asr_model_valid.acc.ave/test_arabic|370|370|0.0|0.0|100.0|0.0|100.0|100.0|
+|decode_asr_ar_er_asr_model_valid.acc.ave_10best/test_ar_em|2301|2301|41.7|58.3|0.0|0.0|58.3|58.3|
+|decode_asr_ar_scr_asr_model_valid.acc.ave/test_arabic|370|370|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_ar_scr_asr_model_valid.acc.ave_10best/test_arabic|370|370|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_audio_asr_model_valid.acc.ave/test_esc50|400|400|0.0|88.5|11.5|0.0|100.0|100.0|
+|decode_asr_audio_asr_model_valid.acc.ave_10best/test_esc50|400|400|2.0|98.0|0.0|0.0|98.0|98.0|
+|decode_asr_dac_asr_model_valid.acc.ave_10best/test_daily_talk_dac|4758|4758|19.3|80.7|0.0|0.0|80.7|80.7|
+|decode_asr_er_asr_model_valid.acc.ave/test_iemocap|942|942|72.1|27.9|0.0|0.0|27.9|27.9|
+|decode_asr_er_asr_model_valid.acc.ave_10best/test_iemocap|942|942|73.9|26.1|0.0|0.0|26.1|26.1|
+|decode_asr_fsd_asr_model_valid.acc.ave/test_asvspoof|71237|71237|99.2|0.8|0.0|0.0|0.8|0.8|
+|decode_asr_fsd_asr_model_valid.acc.ave_10best/test_asvspoof|71237|71237|99.1|0.9|0.0|0.0|0.9|0.9|
+|decode_asr_gid_asr_model_valid.acc.ave/test_voxceleb|4818|4818|99.9|0.1|0.0|0.0|0.1|0.1|
+|decode_asr_gid_asr_model_valid.acc.ave_10best/test_voxceleb|4818|4818|99.9|0.1|0.0|0.0|0.1|0.1|
+|decode_asr_grabo_asr_model_valid.acc.ave/test_grabo|3631|3631|99.6|0.4|0.0|0.0|0.4|0.4|
+|decode_asr_grabo_asr_model_valid.acc.ave_10best/test_grabo|3631|3631|99.7|0.3|0.0|0.0|0.3|0.3|
+|decode_asr_ic_asr_model_valid.acc.ave/test_fsc|3793|9272|99.9|0.1|0.0|0.0|0.1|0.3|
+|decode_asr_ic_asr_model_valid.acc.ave_10best/test_fsc|3793|9272|99.9|0.1|0.0|0.0|0.1|0.3|
+|decode_asr_lid_asr_model_valid.acc.ave/test_voxforge|1800|1800|99.9|0.1|0.0|0.0|0.1|0.1|
+|decode_asr_lid_asr_model_valid.acc.ave_10best/test_voxforge|1800|1800|99.9|0.1|0.0|0.0|0.1|0.1|
+|decode_asr_lt_scr1_asr_model_valid.acc.ave/test_lt_speech_commands|88|88|98.9|1.1|0.0|0.0|1.1|1.1|
+|decode_asr_lt_scr1_asr_model_valid.acc.ave/test_lt_speechcommands|0|0|0.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_lt_scr1_asr_model_valid.acc.ave_10best/test_lt_speech_commands|88|88|98.9|1.1|0.0|0.0|1.1|1.1|
+|decode_asr_ner1_1_asr_model_valid.acc.ave/test_slurp|13078|164549|88.0|6.1|5.9|4.0|16.0|50.0|
+|decode_asr_ner1_1_asr_model_valid.acc.ave_10best/test_slurp|13078|164549|88.3|5.9|5.8|3.8|15.5|48.7|
+|decode_asr_scd_asr_model_valid.acc.ave/test_mustard|138|138|70.3|29.7|0.0|0.0|29.7|29.7|
+|decode_asr_scd_asr_model_valid.acc.ave/test_mustard_plus_plus|92|92|65.2|34.8|0.0|0.0|34.8|34.8|
+|decode_asr_scd_asr_model_valid.acc.ave_10best/test_mustard|138|138|73.2|26.8|0.0|0.0|26.8|26.8|
+|decode_asr_scd_asr_model_valid.acc.ave_10best/test_mustard_plus_plus|92|92|66.3|33.7|0.0|0.0|33.7|33.7|
+|decode_asr_scr_asr_model_valid.acc.ave/test_speechcommands|4890|4890|99.2|0.8|0.0|0.0|0.8|0.8|
+|decode_asr_scr_asr_model_valid.acc.ave_10best/test_speechcommands|4890|4890|99.2|0.8|0.0|0.0|0.8|0.8|
+|decode_asr_snips_ic_asr_model_valid.acc.ave/test_snips|166|166|71.1|28.9|0.0|0.0|28.9|28.9|
+|decode_asr_snips_ic_asr_model_valid.acc.ave_10best/test_snips|166|166|72.3|27.7|0.0|0.0|27.7|27.7|
+|decode_asr_snips_ic_asr_model_valid.acc.best/test_snips|166|166|70.5|29.5|0.0|0.0|29.5|29.5|
+|decode_asr_sp2_asr_model_valid.acc.ave/test|75636|728701|94.0|2.1|3.9|2.7|8.7|24.5|
+|decode_asr_sp2_beam1_asr_model_valid.acc.ave/test|75636|728701|95.0|2.2|2.7|3.3|8.2|24.7|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_acc_asr_model_valid.acc.ave/test_accentdb|3463|25897|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_acc_asr_model_valid.acc.ave_10best/test_accentdb|3463|25897|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_ar_asr_model_valid.acc.ave/test_arabic|370|370|0.0|0.0|100.0|0.0|100.0|100.0|
+|decode_asr_ar_er_asr_model_valid.acc.ave_10best/test_ar_em|2301|11511|59.4|27.8|12.9|22.6|63.2|58.3|
+|decode_asr_ar_scr_asr_model_valid.acc.ave/test_arabic|370|370|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_ar_scr_asr_model_valid.acc.ave_10best/test_arabic|370|370|100.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_audio_asr_model_valid.acc.ave/test_esc50|400|5520|1.2|5.3|93.5|0.0|98.8|100.0|
+|decode_asr_audio_asr_model_valid.acc.ave_10best/test_esc50|400|5520|88.9|5.3|5.8|0.0|11.1|98.0|
+|decode_asr_dac_asr_model_valid.acc.ave_10best/test_daily_talk_dac|4758|35471|42.4|54.6|3.0|21.1|78.7|80.7|
+|decode_asr_er_asr_model_valid.acc.ave/test_iemocap|942|4988|80.1|15.2|4.7|11.3|31.2|27.9|
+|decode_asr_er_asr_model_valid.acc.ave_10best/test_iemocap|942|4988|80.9|14.6|4.6|10.4|29.5|26.1|
+|decode_asr_fsd_asr_model_valid.acc.ave/test_asvspoof|71237|378250|99.5|0.3|0.2|0.6|1.1|0.8|
+|decode_asr_fsd_asr_model_valid.acc.ave_10best/test_asvspoof|71237|378250|99.5|0.3|0.2|0.6|1.2|0.9|
+|decode_asr_gid_asr_model_valid.acc.ave/test_voxceleb|4818|38544|100.0|0.0|0.0|0.0|0.0|0.1|
+|decode_asr_gid_asr_model_valid.acc.ave_10best/test_voxceleb|4818|38544|100.0|0.0|0.0|0.0|0.0|0.1|
+|decode_asr_grabo_asr_model_valid.acc.ave/test_grabo|3631|168247|99.9|0.0|0.1|0.0|0.1|0.4|
+|decode_asr_grabo_asr_model_valid.acc.ave_10best/test_grabo|3631|168247|99.9|0.0|0.0|0.0|0.1|0.3|
+|decode_asr_ic_asr_model_valid.acc.ave/test_fsc|3793|68226|99.9|0.0|0.0|0.0|0.1|0.3|
+|decode_asr_ic_asr_model_valid.acc.ave_10best/test_fsc|3793|68226|99.9|0.0|0.0|0.0|0.1|0.3|
+|decode_asr_lid_asr_model_valid.acc.ave/test_voxforge|1800|3600|99.9|0.0|0.0|0.2|0.3|0.1|
+|decode_asr_lid_asr_model_valid.acc.ave_10best/test_voxforge|1800|3600|99.9|0.0|0.0|0.2|0.3|0.1|
+|decode_asr_lt_scr1_asr_model_valid.acc.ave/test_lt_speech_commands|88|526|98.9|0.2|1.0|0.0|1.1|1.1|
+|decode_asr_lt_scr1_asr_model_valid.acc.ave/test_lt_speechcommands|0|0|0.0|0.0|0.0|0.0|0.0|0.0|
+|decode_asr_lt_scr1_asr_model_valid.acc.ave_10best/test_lt_speech_commands|88|526|98.9|0.2|1.0|0.0|1.1|1.1|
+|decode_asr_ner1_1_asr_model_valid.acc.ave/test_slurp|13078|1083169|90.9|2.4|6.7|4.5|13.7|50.0|
+|decode_asr_ner1_1_asr_model_valid.acc.ave_10best/test_slurp|13078|1083169|91.1|2.3|6.6|4.3|13.2|48.7|
+|decode_asr_scd_asr_model_valid.acc.ave/test_mustard|138|2050|94.5|0.0|5.5|2.5|8.0|29.7|
+|decode_asr_scd_asr_model_valid.acc.ave/test_mustard_plus_plus|92|1368|93.9|0.0|6.1|3.2|9.4|34.8|
+|decode_asr_scd_asr_model_valid.acc.ave_10best/test_mustard|138|2050|95.3|0.0|4.7|2.5|7.2|26.8|
+|decode_asr_scd_asr_model_valid.acc.ave_10best/test_mustard_plus_plus|92|1368|95.3|0.0|4.7|4.4|9.1|33.7|
+|decode_asr_scr_asr_model_valid.acc.ave/test_speechcommands|4890|18327|99.4|0.4|0.3|0.3|0.9|0.8|
+|decode_asr_scr_asr_model_valid.acc.ave_10best/test_speechcommands|4890|18327|99.3|0.4|0.3|0.3|1.0|0.8|
+|decode_asr_snips_ic_asr_model_valid.acc.ave/test_snips|166|2504|92.9|5.3|1.8|2.5|9.6|28.9|
+|decode_asr_snips_ic_asr_model_valid.acc.ave_10best/test_snips|166|2504|92.7|5.4|2.0|2.6|9.9|27.7|
+|decode_asr_snips_ic_asr_model_valid.acc.best/test_snips|166|2504|91.8|6.3|2.0|2.6|10.9|29.5|
+|decode_asr_sp2_asr_model_valid.acc.ave/test|75636|5745269|95.2|0.7|4.1|2.8|7.6|24.5|
+|decode_asr_sp2_beam1_asr_model_valid.acc.ave/test|75636|5745269|96.3|0.7|3.0|3.3|7.0|24.7|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|