训练fastspeech时报错
Created by: ymzlygw
按步骤训练fastspeech时，在训练之前进行Compute Phoneme Duration的时候， 按照说明，预先在 https://github.com/PaddlePaddle/Parakeet 下载了transformerTTS预训练模型作为教学模型参数，放在pre_modle文件夹下，然后运行时报错如下：
**运行命令：**python get_alignments.py \
--use_gpu=1
--output='./alignments'
--data='~/datasets/LJSpeech-1.1'
--config='../pre_model/ljspeech.yaml'
--checkpoint_transformer='../pre_model/step-162000.pdparams' \
报错log：
Traceback (most recent call last): File "get_alignments.py", line 132, in alignments(args) File "get_alignments.py", line 62, in alignments network_cfg['embedding_size'], network_cfg['hidden_size'], KeyError: 'embedding_size'
然后由于下一步训练中的参数可以使用教学模型的alignments.pkl参数和config参数,转而进行train步骤，依旧报错：
运行指令： python train.py \
--use_gpu=1
--data='~/datasets/LJSpeech-1.1'
--alignments_path='pre_model/alignments.pkl'
--output='./experiments'
--config='./pre_model/ljspeech.yaml' \
报错log如下：
{'alignments_path': 'pre_model/alignments.pkl', 'checkpoint': None, 'config': './pre_model/ljspeech.yaml', 'data': '~/datasets/LJSpeech-1.1', 'iteration': None, 'output': './experiments', 'use_gpu': 1} W0701 01:40:03.189592 15764 device_context.cc:252] Please NOTE: device: 0, CUDA Capability: 61, Driver API Version: 10.1, Runtime API Version: 10.0 W0701 01:40:03.192462 15764 device_context.cc:260] device: 0, cuDNN Version: 7.6. 0it [00:00, ?it/s]Rank 0: checkpoint loaded. /root/anaconda3/envs/paddle/lib/python3.7/site-packages/librosa/core/audio.py:161: UserWarning: PySoundFile failed. Trying audioread instead. warnings.warn('PySoundFile failed. Trying audioread instead.') 2020-07-01 01:40:11,265-WARNING: DygraphDataLoader reader thread raised an exception. Exception in thread Thread-3: Traceback (most recent call last): File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/librosa/core/audio.py", line 129, in load with sf.SoundFile(path) as sf_desc: File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/soundfile.py", line 629, in init self._file = self._open(file, mode_int, closefd) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/soundfile.py", line 1184, in _open "Error opening {0!r}: ".format(self.name)) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/soundfile.py", line 1357, in _error_check raise RuntimeError(prefix + _ffi.string(err_str).decode('utf-8', 'replace')) RuntimeError: Error opening '~/datasets/LJSpeech-1.1/wavs/LJ037-0090.wav': System error.
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "/root/anaconda3/envs/paddle/lib/python3.7/threading.py", line 926, in _bootstrap_inner self.run() File "/root/anaconda3/envs/paddle/lib/python3.7/threading.py", line 870, in run self._target(*self._args, **self._kwargs) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/reader.py", line 913, in _reader_thread_loop_for_singleprocess six.reraise(*sys.exc_info()) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/six.py", line 703, in reraise raise value File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/reader.py", line 892, in reader_thread_loop_for_singleprocess for sample in self.batch_reader(): File "/root/AI/Paddle/Parakeet/parakeet/data/datacargo.py", line 112, in next minibatch = [self.dataset[i] for i in index] File "/root/AI/Paddle/Parakeet/parakeet/data/datacargo.py", line 112, in minibatch = [self.dataset[i] for i in index] File "/root/AI/Paddle/Parakeet/parakeet/data/dataset.py", line 47, in getitem return self.get_example(index) File "/root/AI/Paddle/Parakeet/parakeet/data/dataset.py", line 100, in get_example self.cache[i] = self.dataset[i] File "/root/AI/Paddle/Parakeet/parakeet/data/dataset.py", line 47, in getitem return self.get_example(index) File "/root/AI/Paddle/Parakeet/parakeet/data/dataset.py", line 82, in get_example return self.transform(in_data) File "/root/AI/Paddle/Parakeet/examples/fastspeech/data.py", line 114, in call wav, _ = librosa.load(str(fname)) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/librosa/core/audio.py", line 162, in load y, sr_native = __audioread_load(path, offset, duration, dtype) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/librosa/core/audio.py", line 186, in __audioread_load with audioread.audio_open(path) as input_file: File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/audioread/init.py", line 111, in audio_open return BackendClass(path) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/audioread/rawread.py", line 62, in init self._fh = open(filename, 'rb') FileNotFoundError: [Errno 2] No such file or directory: '~/datasets/LJSpeech-1.1/wavs/LJ037-0090.wav'
Traceback (most recent call last): File "train.py", line 166, in main(args) File "train.py", line 110, in main batch = next(iterator) File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/tqdm/_tqdm.py", line 897, in iter for obj in iterable: File "/root/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/reader.py", line 804, in next return self._reader.read_next_var_list() paddle.fluid.core_avx.EnforceNotMet:
C++ Call Stacks (More useful to developers):
0 std::string paddle::platform::GetTraceBackString<std::string const&>(std::string const&, char const*, int) 1 paddle::platform::EnforceNotMet::EnforceNotMet(std::string const&, char const*, int) 2 paddle::operators::reader::BlockingQueue<std::vector<paddle::framework::LoDTensor, std::allocatorpaddle::framework::LoDTensor > >::Receive(std::vector<paddle::framework::LoDTensor, std::allocatorpaddle::framework::LoDTensor >) 3 paddle::operators::reader::PyReader::ReadNext(std::vector<paddle::framework::LoDTensor, std::allocatorpaddle::framework::LoDTensor >) 4 std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> (), std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result, std::__future_base::_Result_base::_Deleter>, unsigned long> >::_M_invoke(std::_Any_data const&) 5 std::__future_base::_State_base::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>&, bool&) 6 ThreadPool::ThreadPool(unsigned long)::{lambda()#1}::operator()() const
Error Message Summary:
Error: Blocking queue is killed because the data reader raises an exception [Hint: Expected killed_ != true, but received killed_:1 == true:1.] at (/paddle/paddle/fluid/operators/reader/blocking_queue.h:141)
关于runerror：数据集下载正确并解压也正确，查找文件也存在，为什么会读取错误呢？
以上2个问题希望开发人员帮忙解答~感谢！