EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

small fixes to python api examples (#269)

Browse Source
This commit is contained in:
Fangjun Kuang
2023-08-14 20:53:36 +08:00
committed by GitHub
parent bc791d4996
commit 313debe45c
2 changed files with 25 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
python-api-examples/speech-recognition-from-microphone-with-endpoint-detection.py
View File

@@ -82,8 +82,7 @@ def get_args():
return parser.parse_args() return parser.parse_args()
def create_recognizer(): def create_recognizer(args):
args = get_args()
assert_file_exists(args.encoder) assert_file_exists(args.encoder)
assert_file_exists(args.decoder) assert_file_exists(args.decoder)
assert_file_exists(args.joiner) assert_file_exists(args.joiner)
@@ -110,7 +109,18 @@ def create_recognizer():
def main(): def main():
recognizer = create_recognizer() args = get_args()
devices = sd.query_devices()
if len(devices) == 0:
print("No microphone devices found")
sys.exit(0)
print(devices)
default_input_device_idx = sd.default.device[0]
print(f'Use default device: {devices[default_input_device_idx]["name"]}')
recognizer = create_recognizer(args)
print("Started! Please speak") print("Started! Please speak")
# The model is using 16 kHz, we use 48 kHz here to demonstrate that # The model is using 16 kHz, we use 48 kHz here to demonstrate that
@@ -145,10 +155,6 @@ def main():
if __name__ == "__main__": if __name__ == "__main__":
devices = sd.query_devices()
print(devices)
default_input_device_idx = sd.default.device[0]
print(f'Use default device: {devices[default_input_device_idx]["name"]}')
try: try:
main() main()

21
python-api-examples/speech-recognition-from-microphone.py
View File

@@ -10,7 +10,7 @@ import argparse
import sys import sys
from pathlib import Path from pathlib import Path
from typing import List, Tuple from typing import List
import sentencepiece as spm import sentencepiece as spm
try: try:
@@ -136,8 +136,7 @@ def get_args():
return parser.parse_args() return parser.parse_args()
def create_recognizer(): def create_recognizer(args):
args = get_args()
assert_file_exists(args.encoder) assert_file_exists(args.encoder)
assert_file_exists(args.decoder) assert_file_exists(args.decoder)
assert_file_exists(args.joiner) assert_file_exists(args.joiner)
@@ -185,13 +184,22 @@ def encode_contexts(args, contexts: List[str]) -> List[List[int]]:
def main(): def main():
args = get_args() args = get_args()
devices = sd.query_devices()
if len(devices) == 0:
print("No microphone devices found")
sys.exit(0)
print(devices)
default_input_device_idx = sd.default.device[0]
print(f'Use default device: {devices[default_input_device_idx]["name"]}')
contexts_list = [] contexts_list = []
contexts = [x.strip().upper() for x in args.contexts.split("/") if x.strip()] contexts = [x.strip().upper() for x in args.contexts.split("/") if x.strip()]
if contexts: if contexts:
print(f"Contexts list: {contexts}") print(f"Contexts list: {contexts}")
contexts_list = encode_contexts(args, contexts) contexts_list = encode_contexts(args, contexts)
recognizer = create_recognizer() recognizer = create_recognizer(args)
print("Started! Please speak") print("Started! Please speak")
# The model is using 16 kHz, we use 48 kHz here to demonstrate that # The model is using 16 kHz, we use 48 kHz here to demonstrate that
@@ -217,11 +225,6 @@ def main():
if __name__ == "__main__": if __name__ == "__main__":
devices = sd.query_devices()
print(devices)
default_input_device_idx = sd.default.device[0]
print(f'Use default device: {devices[default_input_device_idx]["name"]}')
try: try:
main() main()
except KeyboardInterrupt: except KeyboardInterrupt: