Downloads · 30 days
54
1% of all-time downloads
reazonspeech-espnet-v2
reazon-research/reazonspeech-espnet-v2
reazonspeech-espnet-v2 is a automatic speech recognition model from reazon-research. Use it when you need speech turned into text. It is set up for espnet. The card lists the license as apache-2.0.
reazonspeech-espnet-v2 is an automatic speech recognition (ASR) model trained on ReazonSpeech v2.0 corpus.
All-time downloads
4.6K
Public
Repo size
823 MB
Likes
13
Public
Repo makeup
Click a slice to open those files.
.pth823 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- espnet
- License
- apache-2.0
- Access
- Public
- Created
- Jan 29, 2024
- Updated
- Feb 13, 2024
- SHA
- 55332b8a
Model card
From the Hugging Face model README
reazonspeech-espnet-v2
reazonspeech-espnet-v2 is an automatic speech recognition (ASR) model
trained on ReazonSpeech v2.0 corpus.
Model Architecture
The general architecture is the same as reazonspeech-espnet-v1.
-
Conformer-Transducer model with 118.85M parameters.
-
We trained this model for 33 epoch using Adam optimizer. The maximum learning rate was 0.02, with 15000 warmup steps.
-
The training audio files were sampled at 16khz. Make sure that your input audio files have the same sampling rate.
Usage
We recommend to use this model through our reazonspeech library.
from reazonspeech.espnet.asr import load_model, transcribe, audio_from_path
audio = audio_from_path("speech.wav")
model = load_model()
ret = transcribe(model, audio)
print(ret.text)
License
- Task
- Automatic Speech Recognition
- Library
- espnet
- License
- apache-2.0
- Languages
- ja
- Created
- Jan 29, 2024
- Updated
- Feb 13, 2024