aruno14 / speechrecognition Goto Github PK

Can i adjust for italian?

Hey first of all nice job!
But I have a question: Is the model trained with the Common Voice Set or the few words which are written in the test_voice.py file?
Is there one method for training, so could I start only this method and the rest is fininished by itself or what do I have to to reach this goal?

I had a similar issue to this and the listed solution helped:
tensorflow/tensorflow#2117

Added this before model generation.
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config)

I was trying to load dataset but it says that validated.tsv is not available

Hi, I am having trouble extracting the very big 60 GB tar file, because the clips folder is huge. I was wondering what tool you used to extract because every time I do it the time increases exponentially.

Hi,
thanks for your tutorial :)
Im trying to run sentence.py with my dataset but it wont run on TF 11 on Python 3.6.
I couldnt yet figure out the cause :/
Could you please give me a helping hand?

Thanks!

sentence.py:122: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
return [np.array(batch_x_voice), np.array(batch_x_string)], np.array(batch_y_string)
Traceback (most recent call last):
File "sentence.py", line 161, in
model.fit(MySequence(X_voice, X_string, Y_string, batch_size), epochs=epochs, steps_per_epoch=len(X_string)//batch_size)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1064, in fit
steps_per_execution=self._steps_per_execution)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 1112, in init
model=model)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 909, in init
**kwargs)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 781, in init
peek = _process_tensorlike(peek)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 1016, in _process_tensorlike
inputs = nest.map_structure(_convert_numpy_and_scipy, inputs)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/util/nest.py", line 659, in map_structure
structure[0], [func(*x) for x in entries],
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/util/nest.py", line 659, in
structure[0], [func(*x) for x in entries],
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 1011, in _convert_numpy_and_scipy
return ops.convert_to_tensor_v2_with_dispatch(x, dtype=dtype)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py", line 201, in wrapper
return target(*args, **kwargs)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1405, in convert_to_tensor_v2_with_dispatch
value, dtype=dtype, dtype_hint=dtype_hint, name=name)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1415, in convert_to_tensor_v2
as_ref=False)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/profiler/trace.py", line 163, in wrapped
return func(*args, **kwargs)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1540, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/tensor_conversion_registry.py", line 52, in _default_conversion_function
return constant_op.constant(value, dtype, name=name)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 265, in constant
allow_broadcast=True)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 276, in _constant_impl
return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 301, in _constant_eager_impl
t = convert_to_eager_tensor(value, ctx, dtype)
File "/home/semir/keras_tf/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 98, in convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)
ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray).

Also the startup:

2021-02-26 11:41:27.372359: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
voice_max_length: 200
2021-02-26 11:41:28.241010: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-02-26 11:41:28.241466: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcuda.so.1
2021-02-26 11:41:28.278295: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.278646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
coreClock: 1.665GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s
2021-02-26 11:41:28.278677: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
2021-02-26 11:41:28.280171: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11
2021-02-26 11:41:28.280215: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11
2021-02-26 11:41:28.280833: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10
2021-02-26 11:41:28.280985: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10
2021-02-26 11:41:28.282578: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10
2021-02-26 11:41:28.282962: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11
2021-02-26 11:41:28.283060: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8
2021-02-26 11:41:28.283147: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.283502: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.283822: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
2021-02-26 11:41:28.284033: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-02-26 11:41:28.284237: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-02-26 11:41:28.284307: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.284618: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
coreClock: 1.665GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s
2021-02-26 11:41:28.284645: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
2021-02-26 11:41:28.284655: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11
2021-02-26 11:41:28.284664: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11
2021-02-26 11:41:28.284671: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10
2021-02-26 11:41:28.284679: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10
2021-02-26 11:41:28.284687: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10
2021-02-26 11:41:28.284694: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11
2021-02-26 11:41:28.284701: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8
2021-02-26 11:41:28.284732: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.285053: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.285365: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
2021-02-26 11:41:28.285396: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
2021-02-26 11:41:28.624714: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-02-26 11:41:28.624736: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267] 0
2021-02-26 11:41:28.624741: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1280] 0: N
2021-02-26 11:41:28.624853: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.625217: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.625540: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-26 11:41:28.625850: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1406] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10029 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2080 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
2021-02-26 11:41:28.837430: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10
(612, 6, 513)