Please provide the following information when requesting support.
Hardware - GPU (A100/A30/T4/V100): RTX 3090
Hardware - CPU: 11th Intel i9
Operating System: Windows 11 + WSL2
Riva Version:2.8.0
TLT Version (if relevant)
How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)
Hi, I ran this inference code but it does shutdown the docker container soon after inference.
import io
import riva.client
import timestart_time = time.time()
auth = riva.client.Auth(uri=‘localhost:50051’)riva_asr = riva.client.ASRService(auth)
path = “interview-base-audio.wav”
with io.open(path, ‘rb’) as fh:
content = fh.read()config = riva.client.RecognitionConfig()
#req.config.encoding = ra.AudioEncoding.LINEAR_PCM # Audio encoding can be detected from wav
#req.config.sample_rate_hertz = 0 # Sample rate can be detected from wav and resampled if needed
config.language_code = “ko-KR” # Language code of the audio clip
config.max_alternatives = 1 # How many top-N hypotheses to return
config.enable_automatic_punctuation = True # Add punctuation when end of VAD detected
config.audio_channel_count = 1response = riva_asr.offline_recognize(content, config)
asr_best_transcript = response.results[0].alternatives[0].transcript
print(“ASR Transcript:”, asr_best_transcript)end_time = time.time()
print(“\n\nFull Response Message:”)
print(response)elapsed_time = end_time - start_time
print(‘Execution time:’, elapsed_time, ‘seconds’)
After running the code, it returns the transcript correctly but the docker container always is stopped with an error.
Here is the error code from the docker.
BTW, I am using RIVA on WSL2 and tested the code in Windows 11.
log.txt (63.7 KB)