Downloads · 30 days
0
iamanigeeit_ljspeech_tts_fastspeech2_mfa
espnet/iamanigeeit_ljspeech_tts_fastspeech2_mfa
iamanigeeit_ljspeech_tts_fastspeech2_mfa is a text-to-speech model from espnet. Use it when you need text read aloud. It is set up for espnet. The card lists the license as cc-by-4.0.
TTS model trained with Montreal Forced Aligner.
Access
Public
Updated Sep 19, 2026
Repo size
595 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth595 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- espnet
- License
- cc-by-4.0
- Access
- Public
- Created
- Jan 30, 2023
- Updated
- Sep 19, 2026
- SHA
- 25aa254f
Datasets
Model card
From the Hugging Face model README
Usage
pip install espnet
espnet tts "Hello from ESPnet" -o out.wav --model espnet/iamanigeeit_ljspeech_tts_fastspeech2_mfa
import soundfile as sf
from espnet2.bin.tts_inference import Text2Speech
tts = Text2Speech.from_pretrained(model_tag="espnet/iamanigeeit_ljspeech_tts_fastspeech2_mfa")
output = tts("Hello from ESPnet")
sf.write("out.wav", output["wav"].view(-1).cpu().numpy(), tts.fs)
TTS model trained with Montreal Forced Aligner.
To replicate or continue training from the given checkpoint, download LJSpeech,
install MFA
and follow the steps here.
I recommend downloading the pretrained MFA models and running mfa.sh with --train false.
This would help to save time, but one disadvantage is you have to use the MFA g2p for inference (which has a non-standard phoneme set).
- Task
- Text-to-Speech
- Library
- espnet
- License
- cc-by-4.0
- Languages
- en
- Created
- Jan 30, 2023
- Updated
- Sep 19, 2026