MCPcopy Create free account

hub / github.com/ASLP-lab/OSUM / functions

Functions1,852 in github.com/ASLP-lab/OSUM

↓ 1 callersMethodforward_discriminator
(self, batch, device)
OSUM-EChat/tts/cosyvoice/hifigan/hifigan.py:53
↓ 1 callersMethodforward_encoder_chunk
Export interface for c++ call, give input chunk xs, and return output from time 0 to current chunk. Args: xs (torch.
OSUM/wenet/transformer/asr_model.py:414
↓ 1 callersMethodforward_estimator
(self, x, mask, mu, t, spks, cond)
OSUM-EChat/tts/cosyvoice/flow/flow_matching.py:124
↓ 1 callersMethodforward_fsmn
(self, inputs: torch.Tensor, mask: torch.Tensor,
OSUM/wenet/paraformer/attention.py:64
↓ 1 callersMethodforward_full
Full context mode Frontend + Encoder + Decoder + Calc loss Args: speech: (Batch, Length, ...) speech_lengths:
OSUM/wenet/ctl_model/asr_model_ctl.py:104
↓ 1 callersMethodforward_generator
(self, batch, device)
OSUM-EChat/tts/cosyvoice/hifigan/hifigan.py:32
↓ 1 callersMethodforward_layers
(self, x: torch.Tensor, tgt_mask: torch.Tensor, memory: torch.Tensor,
OSUM-EChat/tts/cosyvoice/transformer/decoder.py:169
↓ 1 callersMethodforward_layers
(self, xs: torch.Tensor, chunk_masks: torch.Tensor, pos_emb: torch.Tensor,
OSUM-EChat/tts/cosyvoice/transformer/encoder.py:165
↓ 1 callersMethodforward_layers
(self, xs: torch.Tensor, chunk_masks: torch.Tensor, pos_emb: torch.Tensor,
OSUM-EChat/tts/cosyvoice/transformer/upsample_encoder.py:306
↓ 1 callersMethodforward_layers
(self, x: torch.Tensor, tgt_mask: torch.Tensor, memory: torch.Tensor,
OSUM-EChat/wenet/transformer/decoder.py:203
↓ 1 callersMethodforward_layers
(self, x: torch.Tensor, tgt_mask: torch.Tensor, memory: torch.Tensor,
OSUM/wenet/paraformer/layers.py:469
↓ 1 callersMethodforward_layers
( self, xs: torch.Tensor, att_mask: torch.Tensor, pos_emb: torch.Tensor,
OSUM/wenet/LLM/decoder.py:126
↓ 1 callersMethodforward_layers
(self, x: torch.Tensor, tgt_mask: torch.Tensor, memory: torch.Tensor,
OSUM/wenet/transformer/decoder.py:203
↓ 1 callersMethodforward_layers
(self, xs: torch.Tensor, chunk_masks: torch.Tensor, pos_emb: torch.Tensor,
OSUM/wenet/transformer/encoder.py:185
↓ 1 callersMethodforward_layers_checkpointed
(self, x: torch.Tensor, tgt_mask: torch.Tensor,
OSUM-EChat/tts/cosyvoice/transformer/decoder.py:178
↓ 1 callersMethodforward_layers_checkpointed
(self, xs: torch.Tensor, chunk_masks: torch.Tensor,
OSUM-EChat/tts/cosyvoice/transformer/encoder.py:173
↓ 1 callersMethodforward_layers_checkpointed
(self, x: torch.Tensor, tgt_mask: torch.Tensor,
OSUM-EChat/wenet/transformer/decoder.py:212
↓ 1 callersMethodforward_layers_checkpointed
(self, x: torch.Tensor, tgt_mask: torch.Tensor,
OSUM/wenet/paraformer/layers.py:479
↓ 1 callersMethodforward_layers_checkpointed
(self, xs: torch.Tensor, att_mask: torch.Tensor,
OSUM/wenet/LLM/decoder.py:151
↓ 1 callersMethodforward_layers_checkpointed
(self, x: torch.Tensor, tgt_mask: torch.Tensor,
OSUM/wenet/transformer/decoder.py:212
↓ 1 callersMethodforward_layers_checkpointed
(self, xs: torch.Tensor, chunk_masks: torch.Tensor,
OSUM/wenet/transformer/encoder.py:193
↓ 1 callersMethodforward_one_step
Forward one step. This is only used for decoding. Args: memory: encoded memory, float32 (batch, maxlen_in, feat)
OSUM-EChat/tts/cosyvoice/transformer/decoder.py:187
↓ 1 callersMethodforward_paraformer
( self, speech: torch.Tensor, speech_lengths: torch.Tensor, )
OSUM/wenet/paraformer/paraformer.py:294
↓ 1 callersMethodforward_qkv
( self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor )
OSUM/wenet/paraformer/attention.py:47
↓ 1 callersMethodforward_qkv
( self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor )
OSUM/wenet/paraformer/attention.py:179
↓ 1 callersMethodforward_up_layers
(self, xs: torch.Tensor, chunk_masks: torch.Tensor, pos_emb: torch.Tensor,
OSUM-EChat/tts/cosyvoice/transformer/upsample_encoder.py:313
↓ 1 callersMethodfrontend_cross_lingual
(self, tts_text, prompt_speech_16k, resample_rate)
OSUM-EChat/tts/cosyvoice/cli/frontend.py:206
↓ 1 callersMethodfrontend_instruct
(self, tts_text, spk_id, instruct_text)
OSUM-EChat/tts/cosyvoice/cli/frontend.py:215
↓ 1 callersMethodfrontend_instruct2
(self, tts_text, instruct_text, prompt_speech_16k, resample_rate)
OSUM-EChat/tts/cosyvoice/cli/frontend.py:224
↓ 1 callersMethodfrontend_vc
(self, source_speech_16k, prompt_speech_16k, resample_rate)
OSUM-EChat/tts/cosyvoice/cli/frontend.py:230
↓ 1 callersMethodfrontend_zero_shot_22k
(self, tts_text, prompt_text, prompt_speech_22k, resample_rate=16000)
OSUM-EChat/tts/cosyvoice/cli/frontend.py:166
↓ 1 callersFunctionfsdp_save_model
(model, save_model_path, info_dict)
OSUM-EChat/wenet/utils/fsdp_utils.py:70
↓ 1 callersFunctionfsdp_save_model
(model, save_model_path, info_dict)
OSUM/wenet/utils/fsdp_utils.py:70
↓ 1 callersFunctiongen_ctc_peak_time
(hyp: List[int], blank_id: int = 0)
OSUM/wenet/utils/ctc_utils.py:51
↓ 1 callersFunctiongen_timestamps_from_peak
Args: peaks: ctc peaks time stamp max_duration: max_duration of the sentence frame_rate: frame rate of every time stamp,
OSUM/wenet/utils/ctc_utils.py:63
↓ 1 callersFunctiongen_timestamps_from_peak
(cif_peaks: List[int], num_frames: int, frame_rate=0
OSUM/wenet/paraformer/search.py:113
↓ 1 callersFunctiongenerate_config
(enc_session, ctc_session, args)
OSUM/tools/onnx2horizonbin.py:262
↓ 1 callersFunctiongenerate_lexicon
Generate a lexicon from a word list and token_sym_table. Args: token_sym_table: Token symbol table that mapping token to token ids.
OSUM/tools/k2/prepare_char.py:140
↓ 1 callersMethodgenerate_s2s_no_stream_multi_turn
Multi-turn dialogue
OSUM-EChat/wenet/osum_echat/llmasr_model_instruct_version.py:1166
↓ 1 callersFunctiongenerate_tokens
Generate tokens from the given text file. Args: text_file: A file that contains text lines to generate tokens. Returns: R
OSUM/tools/k2/prepare_char.py:165
↓ 1 callersFunctiongenerate_words
Generate words from the given text file. Args: text_file: A file that contains text lines to generate words. Returns: Ret
OSUM/tools/k2/prepare_char.py:185
↓ 1 callersFunctiongenerator_textgrid
(maxtime, lines, output)
OSUM/wenet/bin/alignment.py:37
↓ 1 callersFunctionget_args
()
OSUM-EChat/tts/cosyvoice/bin/train.py:39
↓ 1 callersFunctionget_args
()
OSUM-EChat/tts/cosyvoice/bin/export_onnx.py:43
↓ 1 callersFunctionget_args
()
OSUM-EChat/tts/cosyvoice/bin/export_jit.py:29
↓ 1 callersFunctionget_args
()
OSUM-EChat/tts/cosyvoice/bin/inference.py:30
↓ 1 callersFunctionget_args
()
OSUM-EChat/tts/cosyvoice/bin/average_model.py:24
↓ 1 callersFunctionget_args
()
OSUM-EChat/wenet/whisper/convert_whisper_to_wenet_config_and_ckpt.py:264
↓ 1 callersFunctionget_args
()
OSUM-EChat/wenet/bin/train.py:62
↓ 1 callersFunctionget_args
()
OSUM-EChat/wenet/bin/average_model.py:24
↓ 1 callersFunctionget_args
()
OSUM/tools/latency_metrics.py:34
↓ 1 callersFunctionget_args
()
OSUM/tools/analyze_dataset.py:43
↓ 1 callersFunctionget_args
()
OSUM/tools/onnx2horizonbin.py:357
↓ 1 callersFunctionget_args
()
OSUM/tools/websocket/performance-ws.py:70
↓ 1 callersFunctionget_args
()
OSUM/wenet/paraformer/convert_paraformer_to_wenet_config_and_ckpt.py:198
↓ 1 callersFunctionget_args
()
OSUM/wenet/cli/transcribe.py:21
↓ 1 callersFunctionget_args
()
OSUM/wenet/whisper/convert_whisper_to_wenet_config_and_ckpt.py:264
↓ 1 callersFunctionget_args
()
OSUM/wenet/ssl/w2vbert/convert_w2vbert_to_wenet_config_and_ckpt.py:163
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/train.py:62
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/export_ipex.py:18
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/recognize4llmasr.py:43
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/recognize_onnx_gpu.py:65
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/recognize.py:35
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/export_jit.py:27
↓ 1 callersFunctionget_args
()
OSUM/wenet/bin/average_model.py:24
↓ 1 callersFunctionget_downsampler
(downsample_rate, ndim=1280)
OSUM-EChat/wenet/osum_echat/downsampler.py:222
↓ 1 callersFunctionget_downsampler
(downsample_rate, ndim=1280)
OSUM/wenet/llm_asr/downsampler.py:222
↓ 1 callersFunctionget_encoding
(name: str = "gpt2", num_languages: int = 99)
OSUM-EChat/tts/cosyvoice/tokenizer/tokenizer.py:170
↓ 1 callersFunctionget_env
(pass_envs)
OSUM/tools/ssh_launcher.py:87
↓ 1 callersFunctionget_frames_timestamp
(alignment, prob, blank_thres=0.999,
OSUM/wenet/bin/alignment.py:55
↓ 1 callersMethodget_label_embedding
(self, labels, labels_lengths)
OSUM/wenet/llm_asr/llmasr_model.py:152
↓ 1 callersFunctionget_labformat
(timestamp, subsample)
OSUM/wenet/bin/alignment.py:88
↓ 1 callersFunctionget_nested_attr
(module, attr_path)
OSUM/wenet/finetune/lora/utils.py:17
↓ 1 callersFunctionget_nested_attribute
(obj, attr_path)
OSUM-EChat/wenet/utils/common.py:327
↓ 1 callersFunctionget_nested_attribute
(obj, attr_path)
OSUM/wenet/utils/common.py:327
↓ 1 callersFunctionget_parser
()
OSUM/tools/text2token.py:38
↓ 1 callersFunctionget_parser
()
OSUM/tools/merge_scp2txt.py:41
↓ 1 callersFunctiongumbel
Sample Gumbel random values with given shape and float dtype. The values are distributed according to the probability density function: .. m
OSUM/wenet/ssl/wav2vec2/quantizer.py:5
↓ 1 callersMethodids2tokens
(self, ids: List[int])
OSUM-EChat/wenet/text/base_tokenizer.py:32
↓ 1 callersMethodids2tokens
(self, ids: List[int])
OSUM/wenet/text/base_tokenizer.py:32
↓ 1 callersFunctionif_have_other_name
(text)
OSUM-EChat/wenet/dataset/process/processor_tag_think.py:520
↓ 1 callersFunctionif_have_other_name
(text)
OSUM-EChat/wenet/dataset/process/processor.py:505
↓ 1 callersFunctionif_have_other_name
(text)
OSUM-EChat/wenet/dataset/process/processor_language_think.py:508
↓ 1 callersMethodinference_bistream
( self, text: Generator, prompt_text: torch.Tensor, prompt_tex
OSUM-EChat/tts/cosyvoice/llm/llm.py:337
↓ 1 callersMethodinference_zero_shot_gxl
(self,tts_text, prompt_text,prompt_speech_16k, stream=False, speed=1.0, text_frontend=True, token_list=None)
OSUM-EChat/tts/cosyvoice/cli/cosyvoice.py:93
↓ 1 callersMethodinference_zero_shot_gz_22k
(self,tts_text, prompt_text,prompt_speech_22k, stream=False, speed=1.0, text_frontend=True, token_list=None)
OSUM-EChat/tts/cosyvoice/cli/cosyvoice.py:104
↓ 1 callersFunctioninit_asr_big_dataset
(data_type, data_list_file_s2t, data_list_file_t2s,
OSUM-EChat/wenet/utils/init_dataset.py:15
↓ 1 callersFunctioninit_asr_dataset
(data_type, data_list_file, tokenizer: Optional[BaseTokenizer] = Non
OSUM-EChat/wenet/utils/init_dataset.py:8
↓ 1 callersFunctioninit_asr_dataset
(data_type, data_list_file, tokenizer: Optional[BaseTokenizer] = Non
OSUM/wenet/utils/init_dataset.py:8
↓ 1 callersFunctioninit_big_dataset
(dataset_type, data_type, data_list_file_s2t, data_list_fil
OSUM-EChat/wenet/utils/init_dataset.py:53
↓ 1 callersFunctioninit_causal_llm
(configs)
OSUM/wenet/utils/init_model.py:176
↓ 1 callersMethodinit_custom_speech_repetition_penalty
OSUM-EChat/wenet/osum_echat/llmasr_model_instruct_version.py:170
↓ 1 callersMethodinit_custom_stop_criteria
创建需要的stop criteria 1. 对于t2t任务,遇到text_eos停止 2. 对于t2s任务,遇到speech_eos停止 3. 对于s2s任务,遇到speech_eos停止 同时要取消原本的停止条件
OSUM-EChat/wenet/osum_echat/llmasr_model_instruct_version.py:184
↓ 1 callersFunctioninit_dataset_and_dataloader
(args, configs, gan)
OSUM-EChat/tts/cosyvoice/utils/train_utils.py:53
↓ 1 callersFunctioninit_dataset_and_dataloader
(args, configs, tokenizer, seed=777)
OSUM-EChat/wenet/utils/train_utils.py:376
↓ 1 callersFunctioninit_dataset_and_dataloader
(args, configs, tokenizer, seed=777)
OSUM/wenet/utils/train_utils.py:373
↓ 1 callersFunctioninit_distributed
(args)
OSUM-EChat/tts/cosyvoice/utils/train_utils.py:39
↓ 1 callersFunctioninit_distributed
(args)
OSUM-EChat/wenet/utils/train_utils.py:262
↓ 1 callersFunctioninit_distributed
(args)
OSUM/wenet/utils/train_utils.py:259
↓ 1 callersFunctioninit_llmasr
(args, configs, is_inference=False)
OSUM-EChat/wenet/osum_echat/init_llmasr.py:12
← previousnext →601–700 of 1,852, ranked by callers