Speaker Manager API

The TTS.tts.utils.speakers.SpeakerManager organize speaker related data and information for 🐸TTS models. It is especially useful for multi-speaker models.

Speaker Manager

class TTS.tts.utils.speakers.SpeakerManager(data_items=None, d_vectors_file_path='', speaker_id_file_path='', encoder_model_path='', encoder_config_path='', use_cuda=False)

Manage the speakers for multi-speaker 🐸TTS models. Load a datafile and parse the information in a way that can be queried by speaker or clip.

There are 3 different scenarios considered:

1. Models using speaker embedding layers. The datafile only maps speaker names to ids used by the embedding layer.

2. Models using d-vectors. The datafile includes a dictionary in the following format.

{
    'clip_name.wav':{
        'name': 'speakerA',
        'embedding'[<d_vector_values>]
    },
    ...
}

3. Computing the d-vectors by the speaker encoder. It loads the speaker encoder model and computes the d-vectors for a given clip or speaker.

Parameters:

• d_vectors_file_path (str, optional) – Path to the metafile including x vectors. Defaults to “”.

• speaker_id_file_path (str, optional) – Path to the metafile that maps speaker names to ids used by

• "". (TTS models. Defaults to) –

• encoder_model_path (str, optional) – Path to the speaker encoder model file. Defaults to “”.

• encoder_config_path (str, optional) – Path to the spealer encoder config file. Defaults to “”.

Examples

>>> # load audio processor and speaker encoder
>>> ap = AudioProcessor(**config.audio)
>>> manager = SpeakerManager(encoder_model_path=encoder_model_path, encoder_config_path=encoder_config_path)
>>> # load a sample audio and compute embedding
>>> waveform = ap.load_wav(sample_wav_path)
>>> mel = ap.melspectrogram(waveform)
>>> d_vector = manager.compute_embeddings(mel.T)

static init_from_config(config, samples=None)

Initialize a speaker manager from config

Parameters:

• config (Coqpit) – Config object.

• samples (Union[List[List], List[Dict]], optional) – List of data samples to parse out the speaker names. Defaults to None.

Returns:

Speaker encoder object.

Return type:

SpeakerEncoder

TTS.tts.utils.speakers.get_speaker_manager(c, data=None, restore_path=None, out_path=None)

Initiate a SpeakerManager instance by the provided config.

Parameters:

• c (Coqpit) – Model configuration.

• restore_path (str) – Path to a previous training folder.

• data (List) – Data samples used in training to infer speakers from. It must be provided if speaker embedding layers is used. Defaults to None.

• out_path (str, optional) – Save the generated speaker IDs to a output path. Defaults to None.

Returns:

initialized and ready to use instance.

Return type:

SpeakerManager

TTS.tts.utils.speakers.load_speaker_mapping(out_path)

Loads speaker mapping if already present.

TTS.tts.utils.speakers.save_speaker_mapping(out_path, speaker_mapping)

Saves speaker mapping if not yet present.