Automatic Speech Recognition
NeMo
Thai
English
speech
streaming
Thai
FastConformer
Transducer
NeMo
Nemotron
Instructions to use iapp/OpenThai2.0-ASR-Streaming with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use iapp/OpenThai2.0-ASR-Streaming with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("iapp/OpenThai2.0-ASR-Streaming") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Card: OpenThai and iApp Technology logos above the title
Browse files
README.md
CHANGED
|
@@ -19,6 +19,8 @@ tags:
|
|
| 19 |
- Nemotron
|
| 20 |
---
|
| 21 |
|
|
|
|
|
|
|
| 22 |
# OpenThai2.0-ASR-Streaming
|
| 23 |
|
| 24 |
Streaming Thai speech-to-text with 0.64B parameters. It writes Thai speech down while people are still talking, 80 to 1120 ms behind the voice, from one model with four latency settings. It is a Thai fine-tune of NVIDIA **Nemotron 3.5 ASR Streaming 0.6B**, made by iApp Technology, and it is the model behind iApp's hosted [OpenThai ASR Realtime](https://iapp.co.th/docs/speech/speech-to-text/realtime) service.
|
|
|
|
| 19 |
- Nemotron
|
| 20 |
---
|
| 21 |
|
| 22 |
+
<p align="center"><img src="https://huggingface.co/datasets/iapp/OpenThai2.0-model-card-assets/resolve/main/openthai-iapp-logos.png" alt="OpenThai 路 iApp Technology" width="460"></p>
|
| 23 |
+
|
| 24 |
# OpenThai2.0-ASR-Streaming
|
| 25 |
|
| 26 |
Streaming Thai speech-to-text with 0.64B parameters. It writes Thai speech down while people are still talking, 80 to 1120 ms behind the voice, from one model with four latency settings. It is a Thai fine-tune of NVIDIA **Nemotron 3.5 ASR Streaming 0.6B**, made by iApp Technology, and it is the model behind iApp's hosted [OpenThai ASR Realtime](https://iapp.co.th/docs/speech/speech-to-text/realtime) service.
|