Args: input_token_ids: (B, Lmax) ,其词表范围是[0, vocab_size1+vocab_size2) dividing_id: int, 第一个词表的个数 embedding1: nn.Embedding

Export interface for c++ call, return eos symbol id of the model

Forward one step. This is only used for decoding. Args: memory: encoded memory, float32 (batch, maxlen_in, feat)

Args: text_tokens_padded: (B, Lmax) text_tokens_lens: (B,) speech_tokens_padded: (B, Lmax2) speech_tokens_lens:

If a sequence is finished, all of its branch should be <eos> Args: pred (torch.Tensor): A int array with shape (batch_si

If a sequence is finished, we only allow one alive branch. This function aims to give one branch a zero score and the rest -inf score. A

Reverse padding for the list of tensors. Args: ys_pad (tensor): The padded tensor (B, Tokenmax). ys_lens (tensor): The lens of to

Create mask for subsequent steps (size, size). This mask is used only in decoder which works in an auto-regressive mode. This means the curre

Args: input: [bs, max_time_step, dim] padding: [bs, max_time_step]

prompt_patern1,prompt,history, wav, prompt_patern2,txt,answer_wav, historcy_batch的内容是： [ big_embed, [

Simple const lr policy

Sample `num_negatives` vectors from feature vectors.

Prepad blank for transducer predictor Args: ys_pad (torch.Tensor): batch of padded target sequences (B, Lmax) blank (int): index

Args: ctc_prefix_results(List[DecodeResult]): ctc prefix beam search results

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

批量进行S2T推理（支持wav.scp格式：key wav_path） Args: wav_scp_path: wav.scp文件路径 output_txt_path: 输出结果文件路径 prompt: 推理使用的提示词

S2T对话（无思考）

ctc forced alignment. Args: torch.Tensor ctc_probs: hidden state sequence, 2d tensor (T, D) torch.Tensor y: id sequence tensor 1d

Compute attention context vector. Args: value (torch.Tensor): Transformed value, size (#batch, n_head, time2, d_k

Convert a lexicon to an FST (in k2 format). Args: lexicon: The input lexicon. See also :func:`read_lexicon` token2id:

Generate a db-domain ploynomial distortion function f(x) = a * x^m * (1-x)^n + x Args: conf: a dict {'a': #int, 'm': #int, 'n':

sentence, ignore_words are both in unicode

sentence, ignore_words are both in unicode

For getting encoding in a streaming fashion Attention!!!!! we apply dropout only once at the whole utterance level in a none

prefix beam search also see wenet.transducer.transducer.beam_search

[mat] = read_mat(file_or_fd) Reads single kaldi matrix, supports ascii and binary. file_or_fd : file, gzipped file, pipe or opened file descrip

read non-linguistic symbol from file. The file format is like below: {NOISE}\n {BRK}\n ... Args: non_lang_sym_path: no

[flt-vec] = read_vec_flt(file_or_fd) Read kaldi float vector, ascii or binary input,

[int-vec] = read_vec_int(file_or_fd) Read kaldi integer vector, ascii or binary input,

Args: infos (dict or None): any info you want to save.

Export interface for c++ call, return sos symbol id of the model