Upload folder using huggingface_hub

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/Step-Audio-2-mini-all-lora1_LibriSpeech_default_performance.json

@@ -0,0 +1,17 @@
+{
+    "task": "ASR",
+    "dataset": "LibriSpeech",
+    "model": "Step-Audio-2-mini-all-lora1",
+    "date": "2025-12-27 17:54:13.091333",
+    "performance": {
+        "test_clean": {
+            "wer": 1.35,
+            "total": 2620
+        },
+        "test_other": {
+            "wer": 2.78,
+            "total": 2939
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank0.log

@@ -0,0 +1,5 @@
+2025-12-27 05:13:36 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:13:36 | INFO | Msg example: {'index': 0, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0003.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}
+2025-12-27 05:25:39 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2025-12-27 05:25:39 | INFO | model Step-Audio-2-mini-all-lora1, data LibriSpeech, all 8 result merged to mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/Step-Audio-2-mini-all-lora1_LibriSpeech.jsonl.
+2025-12-27 05:25:39 | INFO | skip eval for LibriSpeech

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-27 05:08:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:08:26 | INFO | Msg example: {'index': 1, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0012.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-27 05:08:55 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:08:55 | INFO | Msg example: {'index': 2, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0026.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank3.log

@@ -0,0 +1,2 @@
+2025-12-27 05:08:54 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:08:54 | INFO | Msg example: {'index': 3, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0022.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank4.log

@@ -0,0 +1,2 @@
+2025-12-27 05:11:46 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:11:46 | INFO | Msg example: {'index': 4, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0002.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank5.log

@@ -0,0 +1,2 @@
+2025-12-27 05:07:58 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:07:58 | INFO | Msg example: {'index': 5, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0025.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank6.log

@@ -0,0 +1,2 @@
+2025-12-27 05:13:30 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:13:30 | INFO | Msg example: {'index': 6, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0010.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/LibriSpeech/logs/rank7.log

@@ -0,0 +1,2 @@
+2025-12-27 05:08:08 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: LibriSpeech
+2025-12-27 05:08:08 | INFO | Msg example: {'index': 7, 'audio': ['/workspace/intern/pangkaiyu/Kimi-Audio/dataset/LibriSpeech/librispeech/LibriSpeech/test-clean/1320/122617/1320-122617-0001.flac'], 'text': 'Please transcribe the spoken content into written text.', 'meta': {'task': 'ASR', 'interactive': 'Audio-analysis', 'audio_type': 'Speech', 'dataset_series': 'LibriSpeech', 'dataset_name': 'LibriSpeech', 'lang': 'en', 'subset': 'test_clean'}}

mini_ea_new_whole1226/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": "2025-12-27 17:53:59.903449",
+    "performance": {
+        "bus": {
+            "wer": 3.87,
+            "total": 410
+        },
+        "caf": {
+            "wer": 3.84,
+            "total": 410
+        },
+        "ped": {
+            "wer": 3.68,
+            "total": 410
+        },
+        "str": {
+            "wer": 3.92,
+            "total": 410
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank0.log

@@ -0,0 +1,5 @@
+2025-12-27 04:32:34 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:34 | 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'}}
+2025-12-27 04:35:51 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2025-12-27 04:35:51 | INFO | model Step-Audio-2-mini-all-lora1, data chime4_dev-real_kimi, all 8 result merged to mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/Step-Audio-2-mini-all-lora1_chime4_dev-real_kimi.jsonl.
+2025-12-27 04:35:51 | INFO | skip eval for chime4_dev-real_kimi

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:16 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:16 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:18 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:18 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank3.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:16 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:16 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank4.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:16 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:16 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank5.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:15 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:15 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank6.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:31 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:31 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_dev-real_kimi/logs/rank7.log

@@ -0,0 +1,2 @@
+2025-12-27 04:32:15 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_dev-real_kimi
+2025-12-27 04:32:15 | 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_ea_new_whole1226/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": "2025-12-27 17:54:00.665412",
+    "performance": {
+        "bus": {
+            "wer": 6.98,
+            "total": 330
+        },
+        "caf": {
+            "wer": 5.06,
+            "total": 330
+        },
+        "ped": {
+            "wer": 4.69,
+            "total": 330
+        },
+        "str": {
+            "wer": 3.85,
+            "total": 330
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank0.log

@@ -0,0 +1,5 @@
+2025-12-27 04:35:51 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:51 | 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'}}
+2025-12-27 04:38:32 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2025-12-27 04:38:32 | INFO | model Step-Audio-2-mini-all-lora1, data chime4_test-real_kimi, all 8 result merged to mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/Step-Audio-2-mini-all-lora1_chime4_test-real_kimi.jsonl.
+2025-12-27 04:38:32 | INFO | skip eval for chime4_test-real_kimi

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:15 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:15 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:10 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:10 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank3.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:19 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:19 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank4.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:11 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:11 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank5.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:09 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:09 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank6.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:49 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:49 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/chime4_test-real_kimi/logs/rank7.log

@@ -0,0 +1,2 @@
+2025-12-27 04:35:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: chime4_test-real_kimi
+2025-12-27 04:35:13 | 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_ea_new_whole1226/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": "2025-12-27 17:53:58.937775",
+    "performance": {
+        "airport_0dB": {
+            "wer": 23.97,
+            "total": 30
+        },
+        "airport_10dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "airport_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "airport_5dB": {
+            "wer": 8.68,
+            "total": 30
+        },
+        "babble_0dB": {
+            "wer": 35.12,
+            "total": 30
+        },
+        "babble_10dB": {
+            "wer": 3.31,
+            "total": 30
+        },
+        "babble_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "babble_5dB": {
+            "wer": 7.44,
+            "total": 30
+        },
+        "car_0dB": {
+            "wer": 34.3,
+            "total": 30
+        },
+        "car_10dB": {
+            "wer": 6.2,
+            "total": 30
+        },
+        "car_15dB": {
+            "wer": 2.89,
+            "total": 30
+        },
+        "car_5dB": {
+            "wer": 5.79,
+            "total": 30
+        },
+        "exhibition_0dB": {
+            "wer": 28.1,
+            "total": 30
+        },
+        "exhibition_10dB": {
+            "wer": 4.13,
+            "total": 30
+        },
+        "exhibition_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "exhibition_5dB": {
+            "wer": 7.85,
+            "total": 30
+        },
+        "restaurant_0dB": {
+            "wer": 27.69,
+            "total": 30
+        },
+        "restaurant_10dB": {
+            "wer": 1.65,
+            "total": 30
+        },
+        "restaurant_15dB": {
+            "wer": 2.89,
+            "total": 30
+        },
+        "restaurant_5dB": {
+            "wer": 9.09,
+            "total": 30
+        },
+        "station_0dB": {
+            "wer": 23.97,
+            "total": 30
+        },
+        "station_10dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "station_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "station_5dB": {
+            "wer": 9.5,
+            "total": 30
+        },
+        "street_0dB": {
+            "wer": 37.19,
+            "total": 30
+        },
+        "street_10dB": {
+            "wer": 5.37,
+            "total": 30
+        },
+        "street_15dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "street_5dB": {
+            "wer": 11.57,
+            "total": 30
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank0.log

@@ -0,0 +1,4 @@
+2025-12-27 04:31:26 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:26 | 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'}}
+2025-12-27 04:32:34 | INFO | model Step-Audio-2-mini-all-lora1, data noizeus, all 8 result merged to mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/Step-Audio-2-mini-all-lora1_noizeus.jsonl.
+2025-12-27 04:32:34 | INFO | skip eval for noizeus

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:13 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:13 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank3.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:13 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank4.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:13 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank5.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:13 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank6.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:21 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:21 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/noizeus/logs/rank7.log

@@ -0,0 +1,2 @@
+2025-12-27 04:31:13 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: noizeus
+2025-12-27 04:31:13 | 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_ea_new_whole1226/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": "2025-12-27 17:54:09.637565",
+    "performance": {
+        "TEDLIUM-test": {
+            "wer": 2.67,
+            "total": 1155
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank0.log

@@ -0,0 +1,5 @@
+2025-12-27 05:10:22 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2025-12-27 05:10:22 | 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'}}
+2025-12-27 05:13:36 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2025-12-27 05:13:36 | INFO | model Step-Audio-2-mini-all-lora1, data tedlium_test1, all 8 result merged to mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/tedlium_test1/Step-Audio-2-mini-all-lora1_tedlium_test1.jsonl.
+2025-12-27 05:13:36 | INFO | skip eval for tedlium_test1

mini_ea_new_whole1226/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-27 05:05:20 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2025-12-27 05:05:20 | 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_ea_new_whole1226/Step-Audio-2-mini-all-lora1/tedlium_test1/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-27 05:05:54 | INFO | Running Step-Audio-2-mini-all-lora1 on dataset: tedlium_test1
+2025-12-27 05:05:54 | 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'}}