Estonian Espnet2 ASR model

Model description

This is a general-purpose Estonian ASR model trained in the Lab of Language Technology at TalTech.

Intended uses & limitations

This model is intended for general-purpose speech recognition, such as broadcast conversations, interviews, talks, etc.

How to use

from espnet2.bin.asr_inference import Speech2Text
    
model = Speech2Text.from_pretrained(
  "TalTechNLP/espnet2_estonian", 
  lm_weight=0.6, ctc_weight=0.4, beam_size=60
)

# read a sound file with 16k sample rate
import soundfile
speech, rate = soundfile.read("speech.wav")
assert rate == 16000
text, *_ = model(speech)
print(text[0])

Since this model was trained on mostly broadcast speech and texts from the web, it might have problems correctly decoding the following:

• Speech containing technical and other domain-specific terms
• Children's speech
• Non-native speech
• Speech recorded under very noisy conditions or with a microphone far from the speaker
• Very spontaneous and overlapping speech

Training data

Acoustic training data:

Language model training data:

• Estonian National Corpus 2019
• OpenSubtitles
• Speech transcripts

Training procedure

Standard EspNet2 Conformer recipe.

Evaluation results

WER

BibTeX entry and citation info

@inproceedings{watanabe2018espnet,
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  title={{ESPnet}: End-to-End Speech Processing Toolkit},
  year={2018},
  booktitle={Proceedings of Interspeech},
  pages={2207--2211},
  doi={10.21437/Interspeech.2018-1456},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}