Upload folder using huggingface_hub

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/Qwen2.5-Omni-7B-l-after-ea_LibriSpeech_default_performance.json

@@ -0,0 +1,17 @@
+{
+    "task": "ASR",
+    "dataset": "LibriSpeech",
+    "model": "Qwen2.5-Omni-7B-l-after-ea",
+    "date": "2025-12-17 07:37:32.640411",
+    "performance": {
+        "test_clean": {
+            "wer": 2.61,
+            "total": 2620
+        },
+        "test_other": {
+            "wer": 4.7,
+            "total": 2939
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank0.log

@@ -0,0 +1,9 @@
+2025-12-17 07:24:07 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:07 | 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'}}
+2025-12-17 07:24:08 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.
+2025-12-17 07:31:01 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2025-12-17 07:31:11 | INFO | waiting for other ranks to finish, time elapsed: 20s
+2025-12-17 07:31:21 | INFO | waiting for other ranks to finish, time elapsed: 30s
+2025-12-17 07:31:22 | INFO | model Qwen2.5-Omni-7B-l-after-ea, data LibriSpeech, all 8 result merged to 7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/Qwen2.5-Omni-7B-l-after-ea_LibriSpeech.jsonl.
+2025-12-17 07:31:22 | INFO | skip eval for LibriSpeech

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank1.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:11 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:11 | 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'}}
+2025-12-17 07:24:12 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank2.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:09 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:09 | 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'}}
+2025-12-17 07:24:10 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank3.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:09 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:09 | 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'}}
+2025-12-17 07:24:10 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank4.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:09 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:09 | 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'}}
+2025-12-17 07:24:10 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank5.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:11 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:11 | 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'}}
+2025-12-17 07:24:11 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank6.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:10 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:10 | 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'}}
+2025-12-17 07:24:11 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/LibriSpeech/logs/rank7.log

@@ -0,0 +1,4 @@
+2025-12-17 07:24:10 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: LibriSpeech
+2025-12-17 07:24:10 | 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'}}
+2025-12-17 07:24:11 | INFO | Prompt: You are a speech recognition model.
+Transcribe the English audio into text without any punctuation marks.

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/Qwen2.5-Omni-7B-l-after-ea_noizeus_default_performance.json

@@ -0,0 +1,121 @@
+{
+    "task": "ASR",
+    "dataset": "noizeus",
+    "model": "Qwen2.5-Omni-7B-l-after-ea",
+    "date": "2025-12-17 07:37:33.016730",
+    "performance": {
+        "airport_0dB": {
+            "wer": 27.27,
+            "total": 30
+        },
+        "airport_10dB": {
+            "wer": 1.65,
+            "total": 30
+        },
+        "airport_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "airport_5dB": {
+            "wer": 11.98,
+            "total": 30
+        },
+        "babble_0dB": {
+            "wer": 42.56,
+            "total": 30
+        },
+        "babble_10dB": {
+            "wer": 1.65,
+            "total": 30
+        },
+        "babble_15dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "babble_5dB": {
+            "wer": 11.16,
+            "total": 30
+        },
+        "car_0dB": {
+            "wer": 40.91,
+            "total": 30
+        },
+        "car_10dB": {
+            "wer": 4.96,
+            "total": 30
+        },
+        "car_15dB": {
+            "wer": 1.24,
+            "total": 30
+        },
+        "car_5dB": {
+            "wer": 11.57,
+            "total": 30
+        },
+        "exhibition_0dB": {
+            "wer": 28.1,
+            "total": 30
+        },
+        "exhibition_10dB": {
+            "wer": 2.89,
+            "total": 30
+        },
+        "exhibition_15dB": {
+            "wer": 3.31,
+            "total": 30
+        },
+        "exhibition_5dB": {
+            "wer": 9.09,
+            "total": 30
+        },
+        "restaurant_0dB": {
+            "wer": 37.6,
+            "total": 30
+        },
+        "restaurant_10dB": {
+            "wer": 3.72,
+            "total": 30
+        },
+        "restaurant_15dB": {
+            "wer": 1.65,
+            "total": 30
+        },
+        "restaurant_5dB": {
+            "wer": 13.22,
+            "total": 30
+        },
+        "station_0dB": {
+            "wer": 35.12,
+            "total": 30
+        },
+        "station_10dB": {
+            "wer": 2.48,
+            "total": 30
+        },
+        "station_15dB": {
+            "wer": 0.83,
+            "total": 30
+        },
+        "station_5dB": {
+            "wer": 9.92,
+            "total": 30
+        },
+        "street_0dB": {
+            "wer": 36.36,
+            "total": 30
+        },
+        "street_10dB": {
+            "wer": 4.55,
+            "total": 30
+        },
+        "street_15dB": {
+            "wer": 2.07,
+            "total": 30
+        },
+        "street_5dB": {
+            "wer": 15.7,
+            "total": 30
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank0.log

@@ -0,0 +1,4 @@
+2025-12-17 07:31:22 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:31:22 | 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'}}
+2025-12-17 07:31:59 | INFO | model Qwen2.5-Omni-7B-l-after-ea, data noizeus, all 8 result merged to 7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/Qwen2.5-Omni-7B-l-after-ea_noizeus.jsonl.
+2025-12-17 07:31:59 | INFO | skip eval for noizeus

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:01 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:31:01 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-17 07:30:58 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:30:58 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank3.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:16 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:31:16 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank4.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:01 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:31:01 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank5.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:05 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:31:05 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank6.log

@@ -0,0 +1,2 @@
+2025-12-17 07:30:44 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:30:44 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/noizeus/logs/rank7.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:13 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: noizeus
+2025-12-17 07:31:13 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/Qwen2.5-Omni-7B-l-after-ea_voices_dev_clo_default_performance.json

@@ -0,0 +1,25 @@
+{
+    "task": "ASR",
+    "dataset": "voices_dev_clo",
+    "model": "Qwen2.5-Omni-7B-l-after-ea",
+    "date": "2025-12-17 07:37:35.205757",
+    "performance": {
+        "babb": {
+            "wer": 3.77,
+            "total": 364
+        },
+        "musi": {
+            "wer": 3.14,
+            "total": 371
+        },
+        "none": {
+            "wer": 2.53,
+            "total": 380
+        },
+        "tele": {
+            "wer": 3.27,
+            "total": 351
+        }
+    },
+    "eval_method": "qwen2-audio-impl"
+}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank0.log

@@ -0,0 +1,5 @@
+2025-12-17 07:31:59 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:59 | 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'}}
+2025-12-17 07:35:27 | INFO | waiting for other ranks to finish, time elapsed: 10s
+2025-12-17 07:35:27 | INFO | model Qwen2.5-Omni-7B-l-after-ea, data voices_dev_clo, all 8 result merged to 7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/Qwen2.5-Omni-7B-l-after-ea_voices_dev_clo.jsonl.
+2025-12-17 07:35:27 | INFO | skip eval for voices_dev_clo

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank1.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:39 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:39 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank2.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:37 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:37 | 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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank3.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:54 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:54 | INFO | Msg example: {'index': 4, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0159/Lab41-SRI-VOiCES-rm1-babb-sp0159-ch135897-sg0052-mc01-stu-clo-dg100.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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank4.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:40 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:40 | INFO | Msg example: {'index': 5, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0174/Lab41-SRI-VOiCES-rm1-babb-sp0174-ch084280-sg0013-mc02-lav-clo-dg010.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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank5.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:43 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:43 | INFO | Msg example: {'index': 6, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0188/Lab41-SRI-VOiCES-rm1-babb-sp0188-ch135249-sg0029-mc01-stu-clo-dg170.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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank6.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:23 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:23 | INFO | Msg example: {'index': 7, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0205/Lab41-SRI-VOiCES-rm1-babb-sp0205-ch159056-sg0032-mc01-stu-clo-dg020.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'}}

7B_l_after_ea300_ck300/Qwen2.5-Omni-7B-l-after-ea/voices_dev_clo/logs/rank7.log

@@ -0,0 +1,2 @@
+2025-12-17 07:31:52 | INFO | Running Qwen2.5-Omni-7B-l-after-ea on dataset: voices_dev_clo
+2025-12-17 07:31:52 | INFO | Msg example: {'index': 8, 'audio': ['/workspace/intern/pangkaiyu/dg/VOiCES_Box_unzip/Development_Data/Automatic_Speech_Recognition/ASR_dev.v2/rm1/babb/sp_0032-1182/sp0208/Lab41-SRI-VOiCES-rm1-babb-sp0208-ch126851-sg0011-mc02-lav-clo-dg070.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'}}