Commit
•
7ea94ee
1
Parent(s):
d74053c
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,34 +1,3 @@
|
|
| 1 |
-
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
-
library_name: nemo
|
| 5 |
-
datasets:
|
| 6 |
-
- librispeech_asr
|
| 7 |
-
- fisher_corpus
|
| 8 |
-
- Switchboard-1
|
| 9 |
-
- WSJ-0
|
| 10 |
-
- WSJ-1
|
| 11 |
-
- National-Singapore-Corpus-Part-1
|
| 12 |
-
- National-Singapore-Corpus-Part-6
|
| 13 |
-
- vctk
|
| 14 |
-
- VoxPopuli-(EN)
|
| 15 |
-
- Europarl-ASR-(EN)
|
| 16 |
-
- Multilingual-LibriSpeech-(2000-hours)
|
| 17 |
-
- mozilla-foundation/common_voice_7_0
|
| 18 |
-
thumbnail: null
|
| 19 |
-
tags:
|
| 20 |
-
- automatic-speech-recognition
|
| 21 |
-
- speech
|
| 22 |
-
- audio
|
| 23 |
-
- CTC
|
| 24 |
-
- Conformer
|
| 25 |
-
- Transformer
|
| 26 |
-
- pytorch
|
| 27 |
-
- NeMo
|
| 28 |
-
- hf-asr-leaderboard
|
| 29 |
-
- Riva
|
| 30 |
-
license: cc-by-4.0
|
| 31 |
-
|
| 32 |
# This speech tagger performs transcription for Hindi, annotates key entities, predict speaker age, dialiect and intent.
|
| 33 |
|
| 34 |
Model is suitable for voiceAI applications, real-time and offline.
|
|
@@ -70,5 +39,4 @@ print(f'Transcription: {transcription[0]}')
|
|
| 70 |
|
| 71 |
Dataset is from AI4Bharat IndicVoices Hindi V1 and V2 dataset.
|
| 72 |
|
| 73 |
-
https://indicvoices.ai4bharat.org/
|
| 74 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# This speech tagger performs transcription for Hindi, annotates key entities, predict speaker age, dialiect and intent.
|
| 2 |
|
| 3 |
Model is suitable for voiceAI applications, real-time and offline.
|
|
|
|
| 39 |
|
| 40 |
Dataset is from AI4Bharat IndicVoices Hindi V1 and V2 dataset.
|
| 41 |
|
| 42 |
+
https://indicvoices.ai4bharat.org/
|
|
|