服务器启动中...
访问前端页面: http://127.0.0.1:5092
API 端点: POST http://127.0.0.1:5092/v1/audio/transcriptions
服务将使用 4 个线程运行。
[c11e3286-36aa-42e3-a708-1e2c4d8869fb] 正在将 'JUL-887-nv-1760855855.983285.wav' 转换为标准 WAV 格式...
加载模型:parakeet-tdt_ctc-0.6b-ja
[NeMo I 2025-10-19 14:56:05 mixins:181] Tokenizer SentencePieceTokenizer initialized with 3072 tokens
[NeMo W 2025-10-19 14:56:08 modelPT:181] If you intend to do training or fine-tuning, please call the ModelPT.setup_training_data() method and provide a valid configuration file to setup the train data loader.
Train config :
manifest_filepath: null
sample_rate: 16000
batch_size: null
shuffle: true
num_workers: 8
pin_memory: true
max_duration: 30.0
min_duration: 0.1
is_tarred: true
tarred_audio_filepaths: null
shuffle_n: 2048
bucketing_strategy: fully_randomized
bucketing_batch_size: null
use_lhotse: true
use_bucketing: true
batch_duration: 600
quadratic_duration: 15
num_buckets: 30
bucket_duration_bins:
- 1.94375
- 2.55687
- 3.08312
- 3.57138
- 3.98812
- 4.36069
- 4.72375
- 5.078
- 5.434
- 5.78994
- 6.15175
- 6.5175
- 6.8885
- 7.26075
- 7.6495
- 8.05538
- 8.48038
- 8.92763
- 9.40019
- 9.90275
- 10.44594
- 11.04794
- 11.72106
- 12.49338
- 13.40481
- 14.50519
- 15.8975
- 17.80975
- 20.92788
bucket_buffer_size: 20000
shuffle_buffer_size: 10000
[NeMo W 2025-10-19 14:56:08 modelPT:188] If you intend to do validation, please call the ModelPT.setup_validation_data() or ModelPT.setup_multiple_validation_data() method and provide a valid configuration file to setup the validation data loader(s).
Validation config :
manifest_filepath: null
sample_rate: 16000
batch_size: null
shuffle: false
use_start_end_token: false
num_workers: 8
pin_memory: true
is_tarred: false
use_lhotse: true
use_bucketing: true
batch_duration: 600
quadratic_duration: 15
num_buckets: 10
[NeMo W 2025-10-19 14:56:08 modelPT:195] Please call the ModelPT.setup_test_data() or ModelPT.setup_multiple_test_data() method and provide a valid configuration file to setup the test data loader(s).
Test config :
manifest_filepath: null
sample_rate: 16000
batch_size: 256
shuffle: false
use_start_end_token: false
num_workers: 8
pin_memory: true
[NeMo I 2025-10-19 14:56:08 features:305] PADDING: 0
[NeMo I 2025-10-19 14:56:11 rnnt_models:226] Using RNNT Loss : tdt
Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.05, 'omega': 0.1}
[NeMo I 2025-10-19 14:56:11 rnnt_models:226] Using RNNT Loss : tdt
Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.05, 'omega': 0.1}
[NeMo W 2025-10-19 14:56:11 label_looping_base:109] No conditional node support for Cuda.
Cuda graphs with while loops are disabled, decoding speed will be slower
Reason: No `cuda-python` module. Please do `pip install cuda-python>=12.3`
[NeMo I 2025-10-19 14:56:12 rnnt_models:226] Using RNNT Loss : tdt
Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.05, 'omega': 0.1}
[NeMo W 2025-10-19 14:56:12 label_looping_base:109] No conditional node support for Cuda.
Cuda graphs with while loops are disabled, decoding speed will be slower
Reason: No `cuda-python` module. Please do `pip install cuda-python>=12.3`
处理过程中发生严重错误: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Traceback (most recent call last):
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\app.py", line 180, in transcribe_audio
asr_model = nemo_asr.models.ASRModel.from_pretrained(model_name=f"nvidia/{model_list[language]}")
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\nemo\core\classes\common.py", line 822, in from_pretrained
instance = class_.restore_from(
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\nemo\core\classes\modelPT.py", line 493, in restore_from
instance = cls._save_restore_connector.restore_from(
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\nemo\core\connectors\save_restore_connector.py", line 267, in restore_from
loaded_params = self.load_config_and_state_dict(
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\nemo\core\connectors\save_restore_connector.py", line 189, in load_config_and_state_dict
instance = instance.to(map_location)
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\lightning\fabric\utilities\device_dtype_mixin.py", line 55, in to
return super().to(*args, **kwargs)
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\module.py", line 1355, in to
return self._apply(convert)
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\module.py", line 915, in _apply
module._apply(fn)
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\module.py", line 915, in _apply
module._apply(fn)
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\module.py", line 915, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\rnn.py", line 290, in _apply
self._init_flat_weights()
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\rnn.py", line 215, in _init_flat_weights
self.flatten_parameters()
File "E:\AI\Trans-Movie\win-videotrans\parakeet-win-0707\runtime./Lib/site-packages\torch\nn\modules\rnn.py", line 271, in flatten_parameters
torch._cudnn_rnn_flatten_weight(
RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
直接在网页上传,报错如下