mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
702ec03ad8
* add hotword for deploy_tools * Support wfst decoder and contextual biasing (#1039) * Support wfst decoder and contextual biasing * Turn on fstbin compilation --------- Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com> * mv funasr/runtime runtime * Fix crash caused by OOV in hotwords list * funasr infer * funasr infer * funasr infer * funasr infer * funasr infer * fix some bugs about fst hotword; support wfst for websocket server and clients; mv runtime out of funasr; modify relative docs * del onnxruntime/include/gflags * update tensor.h * update run_server.sh * update deploy tools * update deploy tools * update websocket-server * update funasr-wss-server * Remove self loop propagation * Update websocket_protocol_zh.md * Update websocket_protocol_zh.md * update hotword protocol * author zhaomingwork: change hotwords for h5 and java * update hotword protocol * catch exception for json_fst_hws * update hotword on message * update onnx benchmark for ngram&hotword * update docs * update funasr-wss-serve * add NONE for LM_DIR * update docs * update run_server.sh * add whats-new * modify whats-new * update whats-new * update whats-new * Support decoder option for beam searching * update benchmark_onnx_cpp * Support decoder option for websocket * fix bug of CompileHotwordEmbedding * update html client * update docs --------- Co-authored-by: gongbo.gb <35997837+aibulamusi@users.noreply.github.com> Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com> Co-authored-by: 游雁 <zhifu.gzf@alibaba-inc.com>
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
import os
|
|
import time
|
|
import sys
|
|
import librosa
|
|
from funasr.utils.types import str2bool
|
|
|
|
import argparse
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--model_dir', type=str, required=True)
|
|
parser.add_argument('--backend', type=str, default='onnx', help='["onnx", "torch"]')
|
|
parser.add_argument('--wav_file', type=str, default=None, help='amp fallback number')
|
|
parser.add_argument('--quantize', type=str2bool, default=False, help='quantized model')
|
|
parser.add_argument('--intra_op_num_threads', type=int, default=1, help='intra_op_num_threads for onnx')
|
|
parser.add_argument('--output_dir', type=str, default=None, help='amp fallback number')
|
|
args = parser.parse_args()
|
|
|
|
|
|
from funasr.runtime.python.libtorch.funasr_torch import Paraformer
|
|
if args.backend == "onnx":
|
|
from funasr.runtime.python.onnxruntime.funasr_onnx import Paraformer
|
|
|
|
model = Paraformer(args.model_dir, batch_size=1, quantize=args.quantize, intra_op_num_threads=args.intra_op_num_threads)
|
|
|
|
wav_file_f = open(args.wav_file, 'r')
|
|
wav_files = wav_file_f.readlines()
|
|
|
|
output_dir = args.output_dir
|
|
if not os.path.exists(output_dir):
|
|
os.makedirs(output_dir)
|
|
if os.name == 'nt': # Windows
|
|
newline = '\r\n'
|
|
else: # Linux Mac
|
|
newline = '\n'
|
|
text_f = open(os.path.join(output_dir, "text"), "w", newline=newline)
|
|
token_f = open(os.path.join(output_dir, "token"), "w", newline=newline)
|
|
|
|
for i, wav_path_i in enumerate(wav_files):
|
|
wav_name, wav_path = wav_path_i.strip().split()
|
|
result = model(wav_path)
|
|
text_i = "{} {}\n".format(wav_name, result[0]['preds'][0])
|
|
token_i = "{} {}\n".format(wav_name, result[0]['preds'][1])
|
|
text_f.write(text_i)
|
|
text_f.flush()
|
|
token_f.write(token_i)
|
|
token_f.flush()
|
|
text_f.close()
|
|
token_f.close()
|
|
|