MCPcopy Create free account

hub / github.com/KoljaB/RealtimeTTS / functions

Functions1,468 in github.com/KoljaB/RealtimeTTS

↓ 143 callersMethodto
(self, device)
tests/test_pocket_engine.py:62
↓ 63 callersMethodfeed
(self, audio_chunk, samplerate=24000, targetrate=None)
example_rvc/rvc/realtimervc.py:513
↓ 50 callersMethodwrite
(self, message)
tests/multilang_test_textual.py:279
↓ 49 callersMethodplay
Handles the synthesis of text to audio. Plays the audio stream and waits until it is finished playing. If the engine can't co
RealtimeTTS/text_to_stream.py:473
↓ 38 callersMethoditems
(self)
example_rvc/rvc/infer/lib/train/utils.py:458
↓ 36 callersMethodvalues
(self)
example_rvc/rvc/infer/lib/train/utils.py:461
↓ 33 callersMethodremove_weight_norm
(self)
example_rvc/rvc/infer/lib/infer_pack/models.py:338
↓ 31 callersMethodclose
Closes the pipe and stops the worker thread. The _closed flag makes sure no further operations are attempted.
RealtimeTTS/engines/safepipe.py:161
↓ 28 callersMethodkeys
(self)
example_rvc/rvc/infer/lib/train/utils.py:455
↓ 28 callersMethodset_voice
Sets the voice to be used for speech synthesis. Args: voice (Union[str, object]): The voice to be used for speech synthe
RealtimeTTS/engines/base_engine.py:249
↓ 25 callersMethodshutdown
(self)
tests/test_minimax_engine.py:62
↓ 20 callersMethodsend
Synchronously asks the worker thread to perform .send().
RealtimeTTS/engines/safepipe.py:96
↓ 18 callersFunctionget_padding
(kernel_size, dilation=1)
example_rvc/rvc/infer/lib/infer_pack/commons.py:14
↓ 18 callersMethodget_stream_info
Returns the audio stream configuration information suitable for PyAudio. Returns: tuple: A tuple containing the audio fo
RealtimeTTS/engines/base_engine.py:209
↓ 18 callersMethodis_playing
(self)
example_rvc/rvc/realtimervc.py:560
↓ 18 callersMethodstart
Starts audio playback.
RealtimeTTS/stream_player.py:681
↓ 16 callersMethodadd
Add an item to the buffer.
example_rvc/bufferstream.py:14
↓ 16 callersMethodplay_async
Async handling of text to audio synthesis, see play() method.
RealtimeTTS/text_to_stream.py:409
↓ 15 callersMethod__init__
( self, samp_rate, harmonic_num=0, sine_amp=0.1, noise_std=0.003,
example_rvc/rvc/infer/lib/infer_pack/models.py:361
↓ 12 callersMethod__init__
( self, samp_rate, harmonic_num=0, sine_amp=0.1, noise_std=0.003,
example_rvc/rvc/infer/lib/infer_pack/models_onnx.py:297
↓ 12 callersMethodrecv
Synchronously asks the worker to perform .recv() and returns the data.
RealtimeTTS/engines/safepipe.py:114
↓ 12 callersMethodsynthesize
(self, text)
tests/test_minimax_engine.py:59
↓ 12 callersFunctionupdateStatus
(message)
example_fast_api/static/tts.js:139
↓ 11 callersFunctionprintt
(strr)
example_rvc/rvc/infer/modules/train/extract_feature_print.py:46
↓ 11 callersMethodstart
(self, model_name=None)
example_rvc/rvc/realtimervc.py:464
↓ 11 callersMethodstft
(self, x)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:41
↓ 11 callersMethodstop
Signal to stop the buffer stream.
example_rvc/bufferstream.py:18
↓ 10 callersMethod__init__
( self, n_blocks, n_gru, kernel_size, en_de_layers=5, inter_la
example_rvc/rvc/infer/lib/rmvpe.py:377
↓ 10 callersMethodget_voices
Retrieves the voices available from the specific voice source. This method should be overridden by the derived class to fetch the li
RealtimeTTS/engines/base_engine.py:236
↓ 10 callersMethodset_voice_parameters
Sets the voice parameters to be used for speech synthesis. Args: **voice_parameters: The voice parameters to be used for
RealtimeTTS/engines/base_engine.py:262
↓ 10 callersMethodtext
Retrieves the text that has been fed into the stream. Returns: The accumulated text.
RealtimeTTS/text_to_stream.py:902
↓ 9 callersFunctioncheck_device
(device)
example_rvc/rvc/infer/modules/ipex/hijacks.py:90
↓ 9 callersMethodistft
(self, x, freq_pad=None)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:58
↓ 9 callersFunctionprintt
(strr, *args)
example_rvc/rvc/tools/rvc_for_realtime.py:37
↓ 9 callersFunctionreturn_xpu
(device)
example_rvc/rvc/infer/modules/ipex/hijacks.py:98
↓ 8 callersMethod__init__
( self, hidden_channels, kernel_size, dilation_rate, n_layers,
example_rvc/rvc/infer/lib/infer_pack/modules.py:134
↓ 8 callersMethoddecode
(self, hidden, thred=0.03)
example_rvc/rvc/infer/lib/rmvpe.py:587
↓ 8 callersFunctiondownload_file
(url, filename_server, path_local)
example_rvc/download_models.py:24
↓ 8 callersMethodremove_weight_norm
(self)
example_rvc/rvc/infer/lib/infer_pack/modules.py:216
↓ 7 callersMethod_make_success_response
Create a mock successful API response.
tests/test_minimax_engine.py:311
↓ 7 callersMethod_trim_silence
Removes silence from both the start and end of audio_data. If trimming occurs on either end, the corresponding fade is applied.
RealtimeTTS/engines/base_engine.py:184
↓ 7 callersMethodload_engine
Loads the synthesis engine and prepares the audio player for stream playback. This method sets up the engine that will be used for te
RealtimeTTS/text_to_stream.py:218
↓ 6 callersFunctioncreate_directory
(path)
example_rvc/download_models.py:10
↓ 6 callersFunctiondl_model
(link, model_name, dir_name)
example_rvc/rvc/tools/download_models - Kopie.py:10
↓ 6 callersMethodfeed
Feeds text or an iterator to the stream. Args: text_or_iterator: Text or iterator to be fed. Returns:
RealtimeTTS/text_to_stream.py:280
↓ 6 callersMethodflush
(self)
tests/multilang_test_textual.py:283
↓ 6 callersMethodget_f0_post
(self, f0)
example_rvc/rvc/tools/rvc_for_realtime.py:211
↓ 6 callersMethodinfer_from_audio
(self, audio, thred=0.03)
example_rvc/rvc/infer/lib/rmvpe.py:594
↓ 6 callersFunctionprintln
(strr)
example_rvc/rvc/infer/modules/train/preprocess.py:29
↓ 6 callersFunctionprintt
(strr)
example_rvc/rvc/infer/modules/train/extract/extract_f0_rmvpe.py:25
↓ 6 callersFunctionprintt
(strr)
example_rvc/rvc/infer/modules/train/extract/extract_f0_rmvpe_dml.py:23
↓ 6 callersMethodremove_weight_norm
(self)
example_rvc/rvc/infer/lib/infer_pack/models_onnx.py:274
↓ 6 callersMethodsend_command
Send a command to the worker process.
RealtimeTTS/engines/coqui_engine.py:796
↓ 6 callersMethodwrite
Write the message to the queue. Args: msg (str): The message to write.
RealtimeTTS/engines/coqui_engine.py:34
↓ 5 callersMethod_queue_audio
(self, waveform)
RealtimeTTS/engines/moss_tts_engine.py:432
↓ 5 callersFunctioncmb_spectrogram_to_wave
(spec_m, mp, extra_bins_h=None, extra_bins=None)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:349
↓ 5 callersMethodinfer
( self, input_wav: torch.Tensor, block_frame_16k, skip_head, return_le
example_rvc/rvc/tools/rvc_for_realtime.py:355
↓ 5 callersFunctionload_audio
(file, sr)
example_rvc/rvc/infer/lib/audio.py:52
↓ 5 callersMethodpause
(self)
tests/multilang_test_textual.py:655
↓ 5 callersFunctionprintt
(strr)
example_rvc/rvc/infer/modules/train/extract/extract_f0_print.py:23
↓ 5 callersFunctionspectrogram_torch
Convert waveform into Linear-frequency Linear-amplitude spectrogram. Args: y :: (B, T) - Audio waveforms n_fft
example_rvc/rvc/infer/lib/train/mel_processing.py:42
↓ 5 callersMethodstop_stream
Stops the audio stream.
RealtimeTTS/stream_player.py:316
↓ 5 callersMethodverify_sample_rate
Verifies and returns the sample rate. If the sample rate is -1, it will be obtained from the engine's configuration.
RealtimeTTS/engines/base_engine.py:173
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers_123812KB .py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers_33966KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers_537227KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers_123821KB.py:53
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers_new.py:30
↓ 4 callersMethod__init__
(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/layers_537238KB.py:53
↓ 4 callersMethod_create_iterators
Creates iterators required for text-to-audio streaming. This method initializes two types of iterators: 1. `CharIterator`:
RealtimeTTS/text_to_stream.py:984
↓ 4 callersMethod_encode_reference
(self, audio_path: str, transcript: str)
RealtimeTTS/engines/neutts_engine.py:277
↓ 4 callersMethod_ensure_voice_encoded
(self, voice: NeuTTSVoice)
RealtimeTTS/engines/neutts_engine.py:288
↓ 4 callersFunctionlinspace
Generate a linearly spaced 1-D tensor. Arguments: start {[Number]} -- [The starting value of the sequence.] stop {[Number]}
example_rvc/rvc/tools/torchgate/utils.py:45
↓ 4 callersFunctionload_inputs
(path, device, is_half=False)
example_rvc/rvc/infer/lib/jit/__init__.py:9
↓ 4 callersMethodload_model
(checkpoint, tts)
RealtimeTTS/engines/coqui_engine.py:510
↓ 4 callersMethodload_model
Loads the StyleTTS model and necessary components.
RealtimeTTS/engines/style_engine.py:327
↓ 4 callersMethodpush_text
(self, text: str)
example_rvc/xtts_rvc_synthesizer.py:57
↓ 4 callersMethodset_cloning_reference
Send an 'update_reference' command and wait for a response. Args: cloning_reference_wav (Union[str, List[str]]):
RealtimeTTS/engines/coqui_engine.py:803
↓ 4 callersFunctionspectrogram_to_wave
(spec, hop_length, mid_side, mid_side_b2, reverse)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:291
↓ 4 callersMethodtransform
Take input data (audio) to STFT domain. Arguments: input_data {tensor} -- Tensor of floats, with shape (num_batch, num_samples)
example_rvc/rvc/infer/lib/rmvpe.py:84
↓ 4 callersMethodvc
( self, model, net_g, sid, audio0, pitch, pitchf,
example_rvc/rvc/infer/modules/vc/pipeline.py:186
↓ 3 callersMethod__init__
( self, in_channels, out_channels, filter_channels, kernel_size,
example_rvc/rvc/infer/lib/infer_pack/attentions.py:387
↓ 3 callersMethod_apply_slice
(self, waveform, begin, end)
example_rvc/rvc/infer/lib/slicer2.py:64
↓ 3 callersMethod_path_audio_
(self, input, vocal_root, others_root, format, is_hp3=False)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:255
↓ 3 callersFunctioncombine_spectrograms
(specs, mp)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:89
↓ 3 callersMethodcompute_reference_style
Compute the style embedding from a reference audio.
RealtimeTTS/engines/style_engine.py:416
↓ 3 callersFunctioncreate_synthesis_callbacks
(start_time)
tests/style_test.py:20
↓ 3 callersFunctiondl_model
(link, model_name, dir_name)
example_rvc/rvc/tools/download_models.py:10
↓ 3 callersMethoddownload_model
(model_name="v2.0.2", local_models_path=None)
RealtimeTTS/engines/coqui_engine.py:985
↓ 3 callersFunctiondummy_generator
()
tests/write_to_file.py:9
↓ 3 callersFunctionfft_lp_filter
(spec, bin_start, bin_stop)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:426
↓ 3 callersFunctionget_lang_code_from_voice
Determine language code from a voice identifier. If the voice_name is a formula, derive from the first component.
RealtimeTTS/engines/kokoro_engine.py:24
↓ 3 callersFunctionget_synthesizer
(pth_path, device=torch.device("cpu"))
example_rvc/rvc/infer/lib/jit/get_synthesizer.py:4
↓ 3 callersFunctionipex_init
()
example_rvc/rvc/infer/modules/ipex/__init__.py:12
↓ 3 callersMethodis_playing
Checks if the stream is currently playing. Returns: Boolean indicating if the stream is playing.
RealtimeTTS/text_to_stream.py:913
↓ 3 callersFunctionmake_pair
(mix_dir, inst_dir)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/dataset.py:31
↓ 3 callersMethodpoll
Synchronously checks whether data is available. Returns True if data is ready, or False otherwise.
RealtimeTTS/engines/safepipe.py:138
↓ 3 callersMethodpredict
(self, x_mag, aggressiveness=None)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets.py:114
↓ 3 callersMethodset_muted
(self, muted: bool = True)
example_rvc/rvc/realtimervc.py:461
next →1–100 of 1,468, ranked by callers