Checkpoints

            

            
import nemo.collections.tts as nemo_tts
model = nemo_tts.models.<MODEL_BASE_CLASS>.restore_from(restore_path="<path/to/checkpoint/file.nemo>")
        

            

            
import nemo.collections.tts as nemo_tts
model = nemo_tts.models.<MODEL_BASE_CLASS>.from_pretrained(model_name="<MODEL_NAME>")
        

            

            
In [1]: import nemo.collections.tts as nemo_tts

In [2]: nemo_tts.models.FastPitchModel.list_available_models()
Out[2]:
[PretrainedModelInfo(
pretrained_model_name=tts_en_fastpitch,
description=This model is trained on LJSpeech sampled at 22050Hz with and can be used to generate female English voices with an American accent. It is ARPABET-based.,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/tts_en_fastpitch/versions/1.8.1/files/tts_en_fastpitch_align.nemo,
class_=<class 'nemo.collections.tts.models.fastpitch.FastPitchModel'>
),
PretrainedModelInfo(
pretrained_model_name=tts_en_fastpitch_ipa,
description=This model is trained on LJSpeech sampled at 22050Hz with and can be used to generate female English voices with an American accent. It is IPA-based.,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/tts_en_fastpitch/versions/IPA_1.13.0/files/tts_en_fastpitch_align_ipa.nemo,
class_=<class 'nemo.collections.tts.models.fastpitch.FastPitchModel'>
),
PretrainedModelInfo(
pretrained_model_name=tts_en_fastpitch_multispeaker,
description=This model is trained on HiFITTS sampled at 44100Hz with and can be used to generate male and female English voices with an American accent.,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/tts_en_multispeaker_fastpitchhifigan/versions/1.10.0/files/tts_en_fastpitch_multispeaker.nemo,
class_=<class 'nemo.collections.tts.models.fastpitch.FastPitchModel'>
),
PretrainedModelInfo(
pretrained_model_name=tts_de_fastpitch_singlespeaker,
description=This model is trained on a single male speaker data in OpenSLR Neutral German Dataset sampled at 22050Hz and can be used to generate male German voices.,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/tts_de_fastpitchhifigan/versions/1.10.0/files/tts_de_fastpitch_align.nemo,
class_=<class 'nemo.collections.tts.models.fastpitch.FastPitchModel'>
),
PretrainedModelInfo(
pretrained_model_name=tts_de_fastpitch_multispeaker_5,
description=This model is trained on 5 speakers in HUI-Audio-Corpus-German clean subset sampled at 44100Hz with and can be used to generate male and female German voices.,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/tts_de_fastpitch_multispeaker_5/versions/1.11.0/files/tts_de_fastpitch_multispeaker_5.nemo,
class_=<class 'nemo.collections.tts.models.fastpitch.FastPitchModel'>
)]
        

            

            
model = nemo_tts.models.FastPitchModel.from_pretrained(model_name="tts_en_fastpitch")
        

            

            
nemo_tts.models.<MODEL_BASE_CLASS>.list_available_models()
        

            

            
import nemo.collections.tts as nemo_tts
# Load mel spectrogram generator
spec_generator = nemo_tts.models.FastPitchModel.from_pretrained("tts_en_fastpitch")
# Load vocoder
vocoder = nemo_tts.models.HifiGanModel.from_pretrained(model_name="tts_en_hifigan")
# Generate audio
import soundfile as sf
parsed = spec_generator.parse("You can type your sentence here to get nemo to produce speech.")
spectrogram = spec_generator.generate_spectrogram(tokens=parsed)
audio = vocoder.convert_spectrogram_to_audio(spec=spectrogram)
# Save the audio to disk in a file called speech.wav
sf.write("speech.wav", audio.to('cpu').numpy(), 22050)