Add files using upload-large-folder tool

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/Step-Audio-2-mini-all-lora1_chime4_dev-real_kimi_default_performance.json

@@ -0,0 +1,25 @@
+{
+    "task": "ASR",
+    "dataset": "chime4_dev-real_kimi",
+    "model": "Step-Audio-2-mini-all-lora1",
+    "date": "2026-01-05 08:36:28.405629",
+    "performance": {
+        "bus": {
+            "wer": 4.14,
+            "total": 410
+        },
+        "caf": {
+            "wer": 3.9,
+            "total": 410
+        },
+        "ped": {
+            "wer": 3.42,
+            "total": 410
+        },
+        "str": {
+            "wer": 3.66,
+            "total": 410
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank0.log

@@ -0,0 +1,4 @@
+2026-01-05 03:39:29 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:29 | INFO | Msg example: {'index': 1, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C0103_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}
+2026-01-05 03:42:05 | INFO | model Step-Audio-2-mini-all-lora1, data chime4_dev-real_kimi, all 8 result merged to mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/Step-Audio-2-mini-all-lora1_chime4_dev-real_kimi.jsonl.
+2026-01-05 03:42:05 | INFO | skip eval for chime4_dev-real_kimi

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank1.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:17 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:17 | INFO | Msg example: {'index': 2, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C0105_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank2.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:18 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:18 | INFO | Msg example: {'index': 3, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C010C_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank3.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:19 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:19 | INFO | Msg example: {'index': 4, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C010G_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank4.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:18 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:18 | INFO | Msg example: {'index': 5, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C010J_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank5.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:18 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:18 | INFO | Msg example: {'index': 6, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C010K_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank6.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:18 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:18 | INFO | Msg example: {'index': 7, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C010L_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank7.log

@@ -0,0 +1,2 @@
+2026-01-05 03:39:17 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2026-01-05 03:39:17 | INFO | Msg example: {'index': 8, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/dt05_bus_real/F01_050C010O_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-dev-real', 'dataset_name': 'chime4_dev-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/Step-Audio-2-mini-all-lora1_chime4_test-real_kimi_default_performance.json

@@ -0,0 +1,25 @@
+{
+    "task": "ASR",
+    "dataset": "chime4_test-real_kimi",
+    "model": "Step-Audio-2-mini-all-lora1",
+    "date": "2026-01-05 08:36:29.163296",
+    "performance": {
+        "bus": {
+            "wer": 7.62,
+            "total": 330
+        },
+        "caf": {
+            "wer": 5.14,
+            "total": 330
+        },
+        "ped": {
+            "wer": 4.75,
+            "total": 330
+        },
+        "str": {
+            "wer": 4.59,
+            "total": 330
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank0.log

@@ -0,0 +1,4 @@
+2026-01-05 03:42:05 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:42:05 | INFO | Msg example: {'index': 1, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C0202_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}
+2026-01-05 03:44:13 | INFO | model Step-Audio-2-mini-all-lora1, data chime4_test-real_kimi, all 8 result merged to mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/Step-Audio-2-mini-all-lora1_chime4_test-real_kimi.jsonl.
+2026-01-05 03:44:13 | INFO | skip eval for chime4_test-real_kimi

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank1.log

@@ -0,0 +1,2 @@
+2026-01-05 03:41:53 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:41:53 | INFO | Msg example: {'index': 2, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C0204_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank2.log

@@ -0,0 +1,2 @@
+2026-01-05 03:41:46 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:41:46 | INFO | Msg example: {'index': 3, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C0209_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank3.log

@@ -0,0 +1,2 @@
+2026-01-05 03:42:05 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:42:05 | INFO | Msg example: {'index': 4, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C020E_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank4.log

@@ -0,0 +1,2 @@
+2026-01-05 03:41:56 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:41:56 | INFO | Msg example: {'index': 5, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C020F_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank5.log

@@ -0,0 +1,2 @@
+2026-01-05 03:41:55 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:41:55 | INFO | Msg example: {'index': 6, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C020G_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank6.log

@@ -0,0 +1,2 @@
+2026-01-05 03:41:57 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:41:57 | INFO | Msg example: {'index': 7, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C020H_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank7.log

@@ -0,0 +1,2 @@
+2026-01-05 03:41:55 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2026-01-05 03:41:55 | INFO | Msg example: {'index': 8, 'audio': ['/workspace/intern/pangkaiyu/dg/CHIME-4/CHiME4/data/audio/16kHz/isolated_1ch_track/et05_bus_real/F05_440C020I_BUS.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'chime4-test-real', 'dataset_name': 'chime4_test-real_kimi', 'lang': 'en', 'subset': 'bus'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/Step-Audio-2-mini-all-lora1_noizeus_default_performance.json

@@ -0,0 +1,121 @@
+{
+    "task": "ASR",
+    "dataset": "noizeus",
+    "model": "Step-Audio-2-mini-all-lora1",
+    "date": "2026-01-05 08:36:27.449734",
+    "performance": {
+        "airport_0dB": {
+            "wer": 19.01,
+            "total": 30
+        },
+        "airport_10dB": {
+            "wer": 1.24,
+            "total": 30
+        },
+        "airport_15dB": {
+            "wer": 1.24,
+            "total": 30
+        },
+        "airport_5dB": {
+            "wer": 7.44,
+            "total": 30
+        },
+        "babble_0dB": {
+            "wer": 36.36,
+            "total": 30
+        },
+        "babble_10dB": {
+            "wer": 2.89,
+            "total": 30
+        },
+        "babble_15dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "babble_5dB": {
+            "wer": 4.55,
+            "total": 30
+        },
+        "car_0dB": {
+            "wer": 31.4,
+            "total": 30
+        },
+        "car_10dB": {
+            "wer": 3.72,
+            "total": 30
+        },
+        "car_15dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "car_5dB": {
+            "wer": 7.85,
+            "total": 30
+        },
+        "exhibition_0dB": {
+            "wer": 29.34,
+            "total": 30
+        },
+        "exhibition_10dB": {
+            "wer": 4.13,
+            "total": 30
+        },
+        "exhibition_15dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "exhibition_5dB": {
+            "wer": 7.44,
+            "total": 30
+        },
+        "restaurant_0dB": {
+            "wer": 23.97,
+            "total": 30
+        },
+        "restaurant_10dB": {
+            "wer": 1.65,
+            "total": 30
+        },
+        "restaurant_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "restaurant_5dB": {
+            "wer": 7.02,
+            "total": 30
+        },
+        "station_0dB": {
+            "wer": 23.14,
+            "total": 30
+        },
+        "station_10dB": {
+            "wer": 2.89,
+            "total": 30
+        },
+        "station_15dB": {
+            "wer": 1.65,
+            "total": 30
+        },
+        "station_5dB": {
+            "wer": 8.26,
+            "total": 30
+        },
+        "street_0dB": {
+            "wer": 38.43,
+            "total": 30
+        },
+        "street_10dB": {
+            "wer": 4.13,
+            "total": 30
+        },
+        "street_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "street_5dB": {
+            "wer": 11.16,
+            "total": 30
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank0.log

@@ -0,0 +1,5 @@
+2026-01-05 03:38:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:26 | INFO | Msg example: {'index': 0, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp01_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}
+2026-01-05 03:39:29 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2026-01-05 03:39:29 | INFO | model Step-Audio-2-mini-all-lora1, data noizeus, all 8 result merged to mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/Step-Audio-2-mini-all-lora1_noizeus.jsonl.
+2026-01-05 03:39:29 | INFO | skip eval for noizeus

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank1.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:26 | INFO | Msg example: {'index': 1, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp02_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank2.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:26 | INFO | Msg example: {'index': 2, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp03_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank3.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:26 | INFO | Msg example: {'index': 3, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp04_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank4.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:31 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:31 | INFO | Msg example: {'index': 4, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp05_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank5.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:26 | INFO | Msg example: {'index': 5, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp06_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank6.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:26 | INFO | Msg example: {'index': 6, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp07_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/noizeus/logs/rank7.log

@@ -0,0 +1,2 @@
+2026-01-05 03:38:31 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2026-01-05 03:38:31 | INFO | Msg example: {'index': 7, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/Kimi-Audio-Evalkit/data/downloaded_datasets/noizeus/noizeus/airport/0dB/sp08_airport_sn0.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'noizeus', 'dataset_name': 'noizeus', 'lang': 'en', 'subset': 'airport_0dB'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/Step-Audio-2-mini-all-lora1_tedlium_test1_default_performance.json

@@ -0,0 +1,13 @@
+{
+    "task": "ASR",
+    "dataset": "tedlium_test1",
+    "model": "Step-Audio-2-mini-all-lora1",
+    "date": "2026-01-05 08:36:30.049671",
+    "performance": {
+        "TEDLIUM-test": {
+            "wer": 2.49,
+            "total": 1155
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank0.log

@@ -0,0 +1,4 @@
+2026-01-05 03:44:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:44:13 | INFO | Msg example: {'index': 0, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-16.11-27.84-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}
+2026-01-05 03:47:02 | INFO | model Step-Audio-2-mini-all-lora1, data tedlium_test1, all 8 result merged to mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/Step-Audio-2-mini-all-lora1_tedlium_test1.jsonl.
+2026-01-05 03:47:02 | INFO | skip eval for tedlium_test1

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank1.log

@@ -0,0 +1,2 @@
+2026-01-05 03:43:55 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:43:55 | INFO | Msg example: {'index': 1, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-27.84-38.316-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank2.log

@@ -0,0 +1,2 @@
+2026-01-05 03:43:45 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:43:45 | INFO | Msg example: {'index': 2, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-38.316-47.64-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank3.log

@@ -0,0 +1,2 @@
+2026-01-05 03:44:10 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:44:10 | INFO | Msg example: {'index': 3, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-47.64-57.27-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank4.log

@@ -0,0 +1,2 @@
+2026-01-05 03:44:01 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:44:01 | INFO | Msg example: {'index': 4, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-57.27-63.88-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank5.log

@@ -0,0 +1,2 @@
+2026-01-05 03:43:55 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:43:55 | INFO | Msg example: {'index': 5, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-63.88-71.56-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank6.log

@@ -0,0 +1,2 @@
+2026-01-05 03:44:04 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:44:04 | INFO | Msg example: {'index': 6, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-71.56-79.704-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank7.log

@@ -0,0 +1,2 @@
+2026-01-05 03:44:00 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2026-01-05 03:44:00 | INFO | Msg example: {'index': 7, 'audio': ['/workspace/intern/pangkaiyu/dg/tedlium_release1_data/test/wav/MichaelSpecter-79.704-87.33-<o,f0,male>.wav'], 'text': 'Please transcribe the audio content into text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'tedlium', 'dataset_name': 'tedlium_test1', 'lang': 'en', 'subset': 'TEDLIUM-test'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/voices_dev_clo/Step-Audio-2-mini-all-lora1_voices_dev_clo_default_performance.json

@@ -0,0 +1,25 @@
+{
+    "task": "ASR",
+    "dataset": "voices_dev_clo",
+    "model": "Step-Audio-2-mini-all-lora1",
+    "date": "2026-01-05 08:36:40.007096",
+    "performance": {
+        "babb": {
+            "wer": 1.96,
+            "total": 364
+        },
+        "musi": {
+            "wer": 1.56,
+            "total": 371
+        },
+        "none": {
+            "wer": 1.63,
+            "total": 380
+        },
+        "tele": {
+            "wer": 1.65,
+            "total": 351
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/voices_dev_clo/logs/rank0.log

@@ -0,0 +1,4 @@
+2026-01-05 04:13:28 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: voices_dev_clo
+2026-01-05 04:13:28 | INFO | Msg example: {'index': 1, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0112/Lab41-SRI-VOiCES-rm1-babb-sp0112-ch123215-sg0025-mc01-stu-clo-dg080.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'voices', 'dataset_name': 'voices_dev_clo', 'lang': 'en', 'subset': 'babb'}}
+2026-01-05 04:19:18 | INFO | model Step-Audio-2-mini-all-lora1, data voices_dev_clo, all 8 result merged to mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/voices_dev_clo/Step-Audio-2-mini-all-lora1_voices_dev_clo.jsonl.
+2026-01-05 04:19:18 | INFO | skip eval for voices_dev_clo

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/voices_dev_clo/logs/rank1.log

@@ -0,0 +1,2 @@
+2026-01-05 04:12:11 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: voices_dev_clo
+2026-01-05 04:12:11 | INFO | Msg example: {'index': 2, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0122/Lab41-SRI-VOiCES-rm1-babb-sp0122-ch121729-sg0002-mc02-lav-clo-dg060.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'voices', 'dataset_name': 'voices_dev_clo', 'lang': 'en', 'subset': 'babb'}}

mini_whole/mini-encoder+align-whole1226_signal_new1-dpdc-low-lora-1gpu-bs16_1_gckF2000/Step-Audio-2-mini-all-lora1/voices_dev_clo/logs/rank2.log

@@ -0,0 +1,2 @@
+2026-01-05 04:11:53 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: voices_dev_clo
+2026-01-05 04:11:53 | INFO | Msg example: {'index': 3, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0122/Lab41-SRI-VOiCES-rm1-babb-sp0122-ch121730-sg0014-mc01-stu-clo-dg000.wav'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'voices', 'dataset_name': 'voices_dev_clo', 'lang': 'en', 'subset': 'babb'}}