TensorFlowASR
TensorFlowASR copied to clipboard
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
I am trying to train a Chinese model of a conformer. When I train with 4 2080ti, there will be an error in the middle of the epoch: CUDA_ERROR_ILLEGAL_ADDRESS: an...
can you help me ,i do not konw how to debug tensor within pycharm, i can`t see the value within the tensor, it is difficult to debug tensorflow and your...
Hi! I trained the DeepSpeech2 model using the example scripts. With the trained checkpoints I generated a tflite model using the provided conversion script. I can successfully load and allocate...
The error rates shown in https://github.com/TensorSpeech/TensorFlowASR/tree/main/examples/conformer is ```"Greedy: wer: 6.37933683 cer: 2.4757576 on test-clean; wer: 15.7308521 cer: 7.67273521 on test-other". ``` We can not reproduce this error rate. Our error...
I have added below code to ~/TensorFlowASR/examples/conformer/inference/gen_tflite_model.py file. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ print("Started tflite quant conversion") def representative_dataset(): for _ in range(100): data = np.random.rand(1, 2,1, 320) yield [data.astype(np.float32)] converter.representative_dataset = representative_dataset converter.target_spec.supported_ops...
Hello, Im trying to convert a pertained model trained on librispeech, but I run into the following error ``` tensorflow.lite.python.convert_phase.ConverterError: input resource[0] expected type resource != float, the type of...
Hi, my question is that for english, the output of model is directly the index of char If I understand correctly,then it can map between char and sequence. And for...
Purely a question but just wondering if you guys had any thoughts on localised federated training for TensorflowASR? https://www.tensorflow.org/federated The new Pixel6 phones with its TPU name dropped federated learning...
Hi @usimarit I noticed that there are several posts related to my issue like https://github.com/TensorSpeech/TensorFlowASR/issues/168 but I didn't find any clear solutions yet. Do you have any workarounds for this...