audio

audio copied to clipboard

🐛 Describe the bug

I am trying to convert Nvidia NeMo's FilterbankFeaturesTA class to ONNX. Here is my code -

from nemo.collections.asr.parts.preprocessing.features import (
    FilterbankFeatures,
    FilterbankFeaturesTA,
    make_seq_mask_like,
)

_model = FilterbankFeaturesTA(
    sample_rate= 16000,
    # window_size = 0.02,
    # window_stride = 0.01,
    n_window_size = None,
    n_window_stride = None,
    window = "hann",
    normalize = "per_feature",
    n_fft = None,
    preemph = 0.97,
    # features = 64,
    lowfreq = 0,
    highfreq = None,
    log = True,
    log_zero_guard_type = "add",
    log_zero_guard_value = 2 ** -24,
    dither = 1e-5,
    pad_to = 16,
    frame_splicing = 1,
    exact_pad = False,
    pad_value = 0,
    mag_power = 2.0,
    rng = None,
    nb_augmentation_prob = 0.0,
    nb_max_freq = 4000,
    # use_torchaudio = False,
    mel_norm = "slaney",
    stft_exact_pad = False,  
    stft_conv = False,  
)

_model.eval()

example_input_1 = torch.randn(1, 18432)  # Input for x1
example_input_2 = torch.randn(18432)   # Input for x2

# _model(example_input_1, example_input_2)
example_out = _model.forward(example_input_1, example_input_2,)
# example_out
onnx_file_path = "preprocessor.onnx"

args = (example_input_1, example_input_2)
# kwargs = {"seq_len": example_input_2}

onnx_model, _ = torch.onnx.dynamo_export(
    _model,  # Model to export
    *args, 
   #  **kwargs,
    
    export_options=torch.onnx.ExportOptions(
       dynamic_shapes=True,
    ),
)

# Save the ONNX model to file
onnx_model.save(onnx_file_path)

Running this code gives me the following error -

{
	"name": "TypeError",
	"message": "unsupported operand type(s) for //: 'NoneType' and 'int'",
	"stack": "---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[66], line 9
      1 # trying to export features.py FilterbankFeatures to onnx for web inference
      2 # from nemo.collections.asr.parts.preprocessing import FilterbankFeatures
      3 from nemo.collections.asr.parts.preprocessing.features import (
      4     FilterbankFeatures,
      5     FilterbankFeaturesTA,
      6     make_seq_mask_like,
      7 )
----> 9 _model = FilterbankFeaturesTA(
     10     sample_rate= 16000,
     11     # window_size = 0.02,
     12     # window_stride = 0.01,
     13     n_window_size = None,
     14     n_window_stride = None,
     15     window = \"hann\",
     16     normalize = \"per_feature\",
     17     n_fft = None,
     18     preemph = 0.97,
     19     # features = 64,
     20     lowfreq = 0,
     21     highfreq = None,
     22     log = True,
     23     log_zero_guard_type = \"add\",
     24     log_zero_guard_value = 2 ** -24,
     25     dither = 1e-5,
     26     pad_to = 16,
     27     frame_splicing = 1,
     28     exact_pad = False,
     29     pad_value = 0,
     30     mag_power = 2.0,
     31     rng = None,
     32     nb_augmentation_prob = 0.0,
     33     nb_max_freq = 4000,
     34     # use_torchaudio = False,
     35     mel_norm = \"slaney\",
     36     stft_exact_pad = False,  
     37     stft_conv = False,  
     38 )
     40 _model.eval()
     42 example_input_1 = torch.randn(1, 18432)  # Input for x1

File ~/Documents/aakhor/asr/NeMo/nemo/collections/asr/parts/preprocessing/features.py:555, in __init__(self, sample_rate, n_window_size, n_window_stride, normalize, nfilt, n_fft, preemph, lowfreq, highfreq, log, log_zero_guard_type, log_zero_guard_value, dither, window, pad_to, pad_value, mel_norm, use_grads, max_duration, frame_splicing, exact_pad, nb_augmentation_prob, nb_max_freq, mag_power, rng, stft_exact_pad, stft_conv)
    553 self.dither = dither
    554 self.pad_to = pad_to
--> 555 self.pad_value = pad_value
    556 self.n_fft = n_fft
    557 self._mel_spec_extractor: torchaudio.transforms.MelSpectrogram = torchaudio.transforms.MelSpectrogram(
    558     sample_rate=self._sample_rate,
    559     win_length=self.win_length,
   (...)
    568     wkwargs={\"periodic\": False},
    569 )

File ~/miniconda3/envs/nemo/lib/python3.11/site-packages/torchaudio/transforms/_transforms.py:587, in MelSpectrogram.__init__(self, sample_rate, n_fft, win_length, hop_length, f_min, f_max, pad, n_mels, window_fn, power, normalized, wkwargs, center, pad_mode, onesided, norm, mel_scale)
    585 self.n_fft = n_fft
    586 self.win_length = win_length if win_length is not None else n_fft
--> 587 self.hop_length = hop_length if hop_length is not None else self.win_length // 2
    588 self.pad = pad
    589 self.power = power

TypeError: unsupported operand type(s) for //: 'NoneType' and 'int'"
}

Any help in resolving this issue would be appreciated.

Versions

PyTorch version: 2.5.1+cu124 Is debug build: False CUDA used to build PyTorch: 12.4 ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 Clang version: Could not collect CMake version: version 3.22.1 Libc version: glibc-2.35

Python version: 3.11.10 (main, Oct 3 2024, 07:29:13) [GCC 11.2.0] (64-bit runtime) Python platform: Linux-6.8.0-49-generic-x86_64-with-glibc2.35 Is CUDA available: True CUDA runtime version: 11.5.119 CUDA_MODULE_LOADING set to: LAZY GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3060 Nvidia driver version: 550.120 cuDNN version: Could not collect HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 39 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 12 On-line CPU(s) list: 0-11 Vendor ID: GenuineIntel Model name: 12th Gen Intel(R) Core(TM) i5-12400F CPU family: 6 Model: 151 Thread(s) per core: 2 Core(s) per socket: 6 Socket(s): 1 Stepping: 5 CPU max MHz: 4400.0000 CPU min MHz: 800.0000 BogoMIPS: 4992.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize arch_lbr ibt flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 288 KiB (6 instances) L1i cache: 192 KiB (6 instances) L2 cache: 7.5 MiB (6 instances) L3 cache: 18 MiB (1 instance) NUMA node(s): 1 NUMA node0 CPU(s): 0-11 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Versions of relevant libraries: [pip3] numpy==1.24.4 [pip3] nvidia-cublas-cu12==12.4.5.8 [pip3] nvidia-cuda-cupti-cu12==12.4.127 [pip3] nvidia-cuda-nvrtc-cu12==12.4.127 [pip3] nvidia-cuda-runtime-cu12==12.4.127 [pip3] nvidia-cudnn-cu12==9.1.0.70 [pip3] nvidia-cufft-cu12==11.2.1.3 [pip3] nvidia-curand-cu12==10.3.5.147 [pip3] nvidia-cusolver-cu12==11.6.1.9 [pip3] nvidia-cusparse-cu12==12.3.1.170 [pip3] nvidia-cusparselt-cu12==0.6.2 [pip3] nvidia-nccl-cu12==2.21.5 [pip3] nvidia-nvjitlink-cu12==12.4.127 [pip3] nvidia-nvtx-cu12==12.4.127 [pip3] onnx==1.17.0 [pip3] onnxruntime==1.20.1 [pip3] onnxscript==0.1.0.dev20241218 [pip3] open_clip_torch==2.29.0 [pip3] pytorch-lightning==2.4.0 [pip3] pytorch-triton==3.2.0+git0d4682f0 [pip3] torch==2.5.1 [pip3] torchaudio==2.5.1 [pip3] torchdiffeq==0.2.5 [pip3] torchmetrics==1.6.0 [pip3] torchsde==0.2.6 [pip3] torchvision==0.20.1 [pip3] triton==3.1.0 [conda] numpy 1.24.4 py311h64a7726_0 conda-forge [conda] nvidia-cublas-cu12 12.4.5.8 pypi_0 pypi [conda] nvidia-cuda-cupti-cu12 12.4.127 pypi_0 pypi [conda] nvidia-cuda-nvrtc-cu12 12.4.127 pypi_0 pypi [conda] nvidia-cuda-runtime-cu12 12.4.127 pypi_0 pypi [conda] nvidia-cudnn-cu12 9.1.0.70 pypi_0 pypi [conda] nvidia-cufft-cu12 11.2.1.3 pypi_0 pypi [conda] nvidia-curand-cu12 10.3.5.147 pypi_0 pypi [conda] nvidia-cusolver-cu12 11.6.1.9 pypi_0 pypi [conda] nvidia-cusparse-cu12 12.3.1.170 pypi_0 pypi [conda] nvidia-cusparselt-cu12 0.6.2 pypi_0 pypi [conda] nvidia-nccl-cu12 2.21.5 pypi_0 pypi [conda] nvidia-nvjitlink-cu12 12.4.127 pypi_0 pypi [conda] nvidia-nvtx-cu12 12.4.127 pypi_0 pypi [conda] open-clip-torch 2.29.0 pypi_0 pypi [conda] pytorch-lightning 2.4.0 pypi_0 pypi [conda] pytorch-triton 3.2.0+git0d4682f0 pypi_0 pypi [conda] torch 2.5.1 pypi_0 pypi [conda] torchaudio 2.5.1 pypi_0 pypi [conda] torchdiffeq 0.2.5 pypi_0 pypi [conda] torchmetrics 1.6.0 pypi_0 pypi [conda] torchsde 0.2.6 pypi_0 pypi [conda] torchvision 0.20.1 pypi_0 pypi [conda] triton 3.1.0 pypi_0 pypi