RuntimeError: Didn't find engine for operation quantized::linear_prepack NoQEngine on running the docker container about libreasr

[iceychris]

Seems like PyTorch quantization is not supported for your platform.
I didn't have any issues on 64-bit linux with an Intel Processor.

Try applying this diff (git apply fix.diff):

diff --git a/lib/lm.py b/lib/lm.py
index ccb1b68..92f5117 100644
--- a/lib/lm.py
+++ b/lib/lm.py
@@ -90,9 +90,9 @@ def load_lm(conf, lang):
     lm.eval()

     # quantize
-    lm = torch.quantization.quantize_dynamic(
-        lm, {torch.nn.LSTM, torch.nn.Linear}, dtype=torch.qint8
-    )
+    # lm = torch.quantization.quantize_dynamic(
+    #     lm, {torch.nn.LSTM, torch.nn.Linear}, dtype=torch.qint8
+    # )
     lm.eval()

     return lm
diff --git a/lib/model_utils.py b/lib/model_utils.py
index e3b4139..461473e 100644
--- a/lib/model_utils.py
+++ b/lib/model_utils.py
@@ -84,8 +84,8 @@ def load_asr_model(
     # quantize model
     #  we need to this before loading our model
     #  as the saved model is quantized ???
-    model = torch.quantization.quantize_dynamic(
-        model, {torch.nn.LSTM, torch.nn.Linear}, dtype=torch.qint8
-    )
+    # model = torch.quantization.quantize_dynamic(
+    #     model, {torch.nn.LSTM, torch.nn.Linear}, dtype=torch.qint8
+    # )

     return model

and run this:

docker run -it -v $(pwd)/lib:/workspace/lib -p 8080:8080 iceychris/libreasr:latest

This will turn off quantization.

[rplevka]

@iceychris thanks, that did the trick.
Right, it looks like my CPU is unable to do that..here's som CPU info for the record (in case you was interested):

$ cat /proc/cpuinfo 
processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 58
model name	: Intel(R) Core(TM) i5-3337U CPU @ 1.80GHz
stepping	: 9
microcode	: 0x21
cpu MHz		: 1399.993
cache size	: 3072 KB
physical id	: 0
siblings	: 4
core id		: 0
cpu cores	: 2
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
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 rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm cpuid_fault epb pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts md_clear flush_l1d
vmx flags	: vnmi preemption_timer invvpid ept_x_only flexpriority tsc_offset vtpr mtf vapic ept vpid unrestricted_guest
bugs		: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit srbds
bogomips	: 3592.15
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 6
model		: 58
model name	: Intel(R) Core(TM) i5-3337U CPU @ 1.80GHz
stepping	: 9
microcode	: 0x21
cpu MHz		: 1582.269
cache size	: 3072 KB
physical id	: 0
siblings	: 4
core id		: 0
cpu cores	: 2
apicid		: 1
initial apicid	: 1
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
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 rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm cpuid_fault epb pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts md_clear flush_l1d
vmx flags	: vnmi preemption_timer invvpid ept_x_only flexpriority tsc_offset vtpr mtf vapic ept vpid unrestricted_guest
bugs		: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit srbds
bogomips	: 3592.15
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 2
vendor_id	: GenuineIntel
cpu family	: 6
model		: 58
model name	: Intel(R) Core(TM) i5-3337U CPU @ 1.80GHz
stepping	: 9
microcode	: 0x21
cpu MHz		: 1339.551
cache size	: 3072 KB
physical id	: 0
siblings	: 4
core id		: 1
cpu cores	: 2
apicid		: 2
initial apicid	: 2
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
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 rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm cpuid_fault epb pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts md_clear flush_l1d
vmx flags	: vnmi preemption_timer invvpid ept_x_only flexpriority tsc_offset vtpr mtf vapic ept vpid unrestricted_guest
bugs		: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit srbds
bogomips	: 3592.15
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 3
vendor_id	: GenuineIntel
cpu family	: 6
model		: 58
model name	: Intel(R) Core(TM) i5-3337U CPU @ 1.80GHz
stepping	: 9
microcode	: 0x21
cpu MHz		: 1639.644
cache size	: 3072 KB
physical id	: 0
siblings	: 4
core id		: 1
cpu cores	: 2
apicid		: 3
initial apicid	: 3
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
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 rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm cpuid_fault epb pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts md_clear flush_l1d
vmx flags	: vnmi preemption_timer invvpid ept_x_only flexpriority tsc_offset vtpr mtf vapic ept vpid unrestricted_guest
bugs		: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit srbds
bogomips	: 3592.15
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

[iceychris]

Your CPU looks good to me...
Closing this as I just pushed a fix that makes quantization optional by default.