python/FunASR-XL.git

			@@ -5,9 +5,9 @@
			import os.path
			from pathlib import Path
			from typing import List, Union, Tuple
			import json

			import copy
			import torch
			import librosa
			import numpy as np

			@@ -18,7 +18,7 @@
			sentence_postprocess_sentencepiece)
			from .utils.frontend import WavFrontend
			from .utils.timestamp_utils import time_stamp_lfr6_onnx
			from .utils.utils import pad_list, make_pad_mask
			from .utils.utils import pad_list

			logging = get_logger()

			@@ -35,7 +35,8 @@
			plot_timestamp_to: str = "",
			quantize: bool = False,
			intra_op_num_threads: int = 4,
			cache_dir: str = None
			cache_dir: str = None,
			**kwargs
			):
			if not Path(model_dir).exists():
			try:
			@@ -56,25 +57,24 @@
			if not os.path.exists(model_file):
			print(".onnx is not exist, begin to export onnx")
			try:
			from funasr.export.export_model import ModelExport
			from funasr import AutoModel
			except:
			raise "You are exporting onnx, please install funasr and try it again. To install funasr, you could:\n" \
			"\npip3 install -U funasr\n" \
			"For the users in China, you could install with the command:\n" \
			"\npip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple"
			export_model = ModelExport(
			cache_dir=cache_dir,
			onnx=True,
			device="cpu",
			quant=quantize,
			)
			export_model.export(model_dir)

			model = AutoModel(model=model_dir)
			model_dir = model.export(type="onnx", quantize=quantize, **kwargs)

			config_file = os.path.join(model_dir, 'config.yaml')
			cmvn_file = os.path.join(model_dir, 'am.mvn')
			config = read_yaml(config_file)
			token_list = os.path.join(model_dir, 'tokens.json')
			with open(token_list, 'r', encoding='utf-8') as f:
			token_list = json.load(f)

			self.converter = TokenIDConverter(config['token_list'])
			self.converter = TokenIDConverter(token_list)
			self.tokenizer = CharTokenizer()
			self.frontend = WavFrontend(
			cmvn_file=cmvn_file,
			@@ -244,7 +244,8 @@
			plot_timestamp_to: str = "",
			quantize: bool = False,
			intra_op_num_threads: int = 4,
			cache_dir: str = None
			cache_dir: str = None,
			**kwargs
			):

			if not Path(model_dir).exists():
			@@ -267,22 +268,32 @@
			model_bb_file = os.path.join(model_dir, 'model.onnx')
			model_eb_file = os.path.join(model_dir, 'model_eb.onnx')

			token_list_file = os.path.join(model_dir, 'tokens.txt')
			self.vocab = {}
			with open(Path(token_list_file), 'r') as fin:
			for i, line in enumerate(fin.readlines()):
			self.vocab[line.strip()] = i
			if not (os.path.exists(model_eb_file) and os.path.exists(model_bb_file)):
			print(".onnx is not exist, begin to export onnx")
			try:
			from funasr import AutoModel
			except:
			raise "You are exporting onnx, please install funasr and try it again. To install funasr, you could:\n" \
			"\npip3 install -U funasr\n" \
			"For the users in China, you could install with the command:\n" \
			"\npip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple"

			#if quantize:
			# model_file = os.path.join(model_dir, 'model_quant.onnx')
			#if not os.path.exists(model_file):
			# logging.error(".onnx model not exist, please export first.")
			model = AutoModel(model=model_dir)
			model_dir = model.export(type="onnx", quantize=quantize, **kwargs)

			config_file = os.path.join(model_dir, 'config.yaml')
			cmvn_file = os.path.join(model_dir, 'am.mvn')
			config = read_yaml(config_file)
			token_list = os.path.join(model_dir, 'tokens.json')
			with open(token_list, 'r', encoding='utf-8') as f:
			token_list = json.load(f)

			# revert token_list into vocab dict
			self.vocab = {}
			for i, token in enumerate(token_list):
			self.vocab[token] = i

			self.converter = TokenIDConverter(config['token_list'])
			self.converter = TokenIDConverter(token_list)
			self.tokenizer = CharTokenizer()
			self.frontend = WavFrontend(
			cmvn_file=cmvn_file,
			@@ -309,7 +320,7 @@
			# index from bias_embed
			bias_embed = bias_embed.transpose(1, 0, 2)
			_ind = np.arange(0, len(hotwords)).tolist()
			bias_embed = bias_embed[_ind, hotwords_length.cpu().numpy().tolist()]
			bias_embed = bias_embed[_ind, hotwords_length.tolist()]
			waveform_list = self.load_data(wav_content, self.frontend.opts.frame_opts.samp_freq)
			waveform_nums = len(waveform_list)
			asr_res = []
			@@ -336,7 +347,7 @@
			hotwords = hotwords.split(" ")
			hotwords_length = [len(i) - 1 for i in hotwords]
			hotwords_length.append(0)
			hotwords_length = torch.Tensor(hotwords_length).to(torch.int32)
			hotwords_length = np.array(hotwords_length)
			# hotwords.append('<s>')
			def word_map(word):
			hotwords = []
			@@ -346,11 +357,12 @@
			logging.warning("oov character {} found in hotword {}, replaced by <unk>".format(c, word))
			else:
			hotwords.append(self.vocab[c])
			return torch.tensor(hotwords)
			return np.array(hotwords)
			hotword_int = [word_map(i) for i in hotwords]
			# import pdb; pdb.set_trace()
			hotword_int.append(torch.tensor([1]))
			hotword_int.append(np.array([1]))
			hotwords = pad_list(hotword_int, pad_value=0, max_len=10)
			# import pdb; pdb.set_trace()
			return hotwords, hotwords_length

			def bb_infer(self, feats: np.ndarray,
			@@ -359,7 +371,7 @@
			return outputs

			def eb_infer(self, hotwords, hotwords_length):
			outputs = self.ort_infer_eb([hotwords.to(torch.int32).numpy(), hotwords_length.to(torch.int32).numpy()])
			outputs = self.ort_infer_eb([hotwords.astype(np.int32), hotwords_length.astype(np.int32)])
			return outputs

			def decode(self, am_scores: np.ndarray, token_nums: int) -> List[str]:
			@@ -389,4 +401,10 @@
			token = self.converter.ids2tokens(token_int)
			token = token[:valid_token_num-self.pred_bias]
			# texts = sentence_postprocess(token)
			return token
			return token


			class SeacoParaformer(ContextualParaformer):
			def __init__(self, args, *kwargs):
			super().__init__(args, *kwargs)
			# no difference with contextual_paraformer in method of calling onnx models