Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,809 @@
 ---
-license: cc-by-nc-4.0
+license: cc-by-4.0
+track_downloads: true
+language:
+- en
+- es
+- fr
+- de
+- bg
+- hr
+- cs
+- da
+- nl
+- et
+- fi
+- el
+- hu
+- it
+- lv
+- lt
+- mt
+- pl
+- pt
+- ro
+- sk
+- sl
+- sv
+- ru
+- uk
+
+pipeline_tag: automatic-speech-recognition
+library_name: nemo
+datasets:
+- nvidia/Granary
+- nemo/asr-set-3.0
+thumbnail: null
+tags:
+- automatic-speech-recognition
+- speech
+- audio
+- Transducer
+- TDT
+- FastConformer
+- Conformer
+- pytorch
+- NeMo
+- hf-asr-leaderboard
+widget:
+- example_title: Librispeech sample 1
+  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
+- example_title: Librispeech sample 2
+  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
+model-index:
+- name: parakeet-tdt-0.6b-v3
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: AMI (Meetings test)
+      type: edinburghcstr/ami
+      config: ihm
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 11.31
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Earnings-22
+      type: revdotcom/earnings22
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 11.42
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: GigaSpeech
+      type: speechcolab/gigaspeech
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 9.59
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: LibriSpeech (clean)
+      type: librispeech_asr
+      config: other
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 1.93
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: LibriSpeech (other)
+      type: librispeech_asr
+      config: other
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 3.59
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: SPGI Speech
+      type: kensho/spgispeech
+      config: test
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 3.97
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: tedlium-v3
+      type: LIUM/tedlium
+      config: release1
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 2.75
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Vox Populi
+      type: facebook/voxpopuli
+      config: en
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 6.14
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: bg_bg
+      split: test
+      args:
+        language: bg
+    metrics:
+    - name: Test WER (Bg)
+      type: wer
+      value: 12.64
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: cs_cz
+      split: test
+      args:
+        language: cs
+    metrics:
+    - name: Test WER (Cs)
+      type: wer
+      value: 11.01
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: da_dk
+      split: test
+      args:
+        language: da
+    metrics:
+    - name: Test WER (Da)
+      type: wer
+      value: 18.41
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: de_de
+      split: test
+      args:
+        language: de
+    metrics:
+    - name: Test WER (De)
+      type: wer
+      value: 5.04
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: el_gr
+      split: test
+      args:
+        language: el
+    metrics:
+    - name: Test WER (El)
+      type: wer
+      value: 20.70
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: en_us
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER (En)
+      type: wer
+      value: 4.85
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: es_419
+      split: test
+      args:
+        language: es
+    metrics:
+    - name: Test WER (Es)
+      type: wer
+      value: 3.45
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: et_ee
+      split: test
+      args:
+        language: et
+    metrics:
+    - name: Test WER (Et)
+      type: wer
+      value: 17.73
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: fi_fi
+      split: test
+      args:
+        language: fi
+    metrics:
+    - name: Test WER (Fi)
+      type: wer
+      value: 13.21
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: fr_fr
+      split: test
+      args:
+        language: fr
+    metrics:
+    - name: Test WER (Fr)
+      type: wer
+      value: 5.15
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: hr_hr
+      split: test
+      args:
+        language: hr
+    metrics:
+    - name: Test WER (Hr)
+      type: wer
+      value: 12.46
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: hu_hu
+      split: test
+      args:
+        language: hu
+    metrics:
+    - name: Test WER (Hu)
+      type: wer
+      value: 15.72
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: it_it
+      split: test
+      args:
+        language: it
+    metrics:
+    - name: Test WER (It)
+      type: wer
+      value: 3.00
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: lt_lt
+      split: test
+      args:
+        language: lt
+    metrics:
+    - name: Test WER (Lt)
+      type: wer
+      value: 20.35
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: lv_lv
+      split: test
+      args:
+        language: lv
+    metrics:
+    - name: Test WER (Lv)
+      type: wer
+      value: 22.84
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: mt_mt
+      split: test
+      args:
+        language: mt
+    metrics:
+    - name: Test WER (Mt)
+      type: wer
+      value: 20.46
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: nl_nl
+      split: test
+      args:
+        language: nl
+    metrics:
+    - name: Test WER (Nl)
+      type: wer
+      value: 7.48
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: pl_pl
+      split: test
+      args:
+        language: pl
+    metrics:
+    - name: Test WER (Pl)
+      type: wer
+      value: 7.31
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: pt_br
+      split: test
+      args:
+        language: pt
+    metrics:
+    - name: Test WER (Pt)
+      type: wer
+      value: 4.76
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: ro_ro
+      split: test
+      args:
+        language: ro
+    metrics:
+    - name: Test WER (Ro)
+      type: wer
+      value: 12.44
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: ru_ru
+      split: test
+      args:
+        language: ru
+    metrics:
+    - name: Test WER (Ru)
+      type: wer
+      value: 5.51
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: sk_sk
+      split: test
+      args:
+        language: sk
+    metrics:
+    - name: Test WER (Sk)
+      type: wer
+      value: 8.82
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: sl_si
+      split: test
+      args:
+        language: sl
+    metrics:
+    - name: Test WER (Sl)
+      type: wer
+      value: 24.03
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: sv_se
+      split: test
+      args:
+        language: sv
+    metrics:
+    - name: Test WER (Sv)
+      type: wer
+      value: 15.08
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: uk_ua
+      split: test
+      args:
+        language: uk
+    metrics:
+    - name: Test WER (Uk)
+      type: wer
+      value: 6.79
+  # Multilingual LibriSpeech ASR Results
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Multilingual LibriSpeech
+      type: facebook/multilingual_librispeech
+      config: spanish
+      split: test
+      args:
+        language: es
+    metrics:
+    - name: Test WER (Es)
+      type: wer
+      value: 4.39
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Multilingual LibriSpeech
+      type: facebook/multilingual_librispeech
+      config: french
+      split: test
+      args:
+        language: fr
+    metrics:
+    - name: Test WER (Fr)
+      type: wer
+      value: 4.97
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Multilingual LibriSpeech
+      type: facebook/multilingual_librispeech
+      config: italian
+      split: test
+      args:
+        language: it
+    metrics:
+    - name: Test WER (It)
+      type: wer
+      value: 10.08
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Multilingual LibriSpeech
+      type: facebook/multilingual_librispeech
+      config: dutch
+      split: test
+      args:
+        language: nl
+    metrics:
+    - name: Test WER (Nl)
+      type: wer
+      value: 12.78
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Multilingual LibriSpeech
+      type: facebook/multilingual_librispeech
+      config: polish
+      split: test
+      args:
+        language: pl
+    metrics:
+    - name: Test WER (Pl)
+      type: wer
+      value: 7.28
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Multilingual LibriSpeech
+      type: facebook/multilingual_librispeech
+      config: portuguese
+      split: test
+      args:
+        language: pt
+    metrics:
+    - name: Test WER (Pt)
+      type: wer
+      value: 7.50
+  # CoVoST2 ASR Results
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: de
+      split: test
+      args:
+        language: de
+    metrics:
+    - name: Test WER (De)
+      type: wer
+      value: 4.84
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: en
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER (En)
+      type: wer
+      value: 6.80
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: es
+      split: test
+      args:
+        language: es
+    metrics:
+    - name: Test WER (Es)
+      type: wer
+      value: 3.41
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: et
+      split: test
+      args:
+        language: et
+    metrics:
+    - name: Test WER (Et)
+      type: wer
+      value: 22.04
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: fr
+      split: test
+      args:
+        language: fr
+    metrics:
+    - name: Test WER (Fr)
+      type: wer
+      value: 6.05
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: it
+      split: test
+      args:
+        language: it
+    metrics:
+    - name: Test WER (It)
+      type: wer
+      value: 3.69
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: lv
+      split: test
+      args:
+        language: lv
+    metrics:
+    - name: Test WER (Lv)
+      type: wer
+      value: 38.36
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: nl
+      split: test
+      args:
+        language: nl
+    metrics:
+    - name: Test WER (Nl)
+      type: wer
+      value: 6.50
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: pt
+      split: test
+      args:
+        language: pt
+    metrics:
+    - name: Test WER (Pt)
+      type: wer
+      value: 3.96
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: ru
+      split: test
+      args:
+        language: ru
+    metrics:
+    - name: Test WER (Ru)
+      type: wer
+      value: 3.00
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: sl
+      split: test
+      args:
+        language: sl
+    metrics:
+    - name: Test WER (Sl)
+      type: wer
+      value: 31.80
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: sv
+      split: test
+      args:
+        language: sv
+    metrics:
+    - name: Test WER (Sv)
+      type: wer
+      value: 20.16
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: CoVoST2
+      type: covost2
+      config: uk
+      split: test
+      args:
+        language: uk
+    metrics:
+    - name: Test WER (Uk)
+      type: wer
+      value: 5.10
+metrics:
+- wer
 ---
+
+# **<span style="color:#76b900;">🦜 parakeet-tdt-0.6b-v3: Multilingual Speech-to-Text Model</span>**
+
+<style>
+img {
+ display: inline;
+}
+</style>
+
+[![Model architecture](https://img.shields.io/badge/Model_Arch-FastConformer--TDT-blue#model-badge)](#model-architecture)
+| [![Model size](https://img.shields.io/badge/Params-0.6B-green#model-badge)](#model-architecture)
+| [![Language](https://img.shields.io/badge/Language-EU_Languages-blue#model-badge)](#datasets)
+
+## <span style="color:#466f00;">Description:</span>
+
+`parakeet-tdt-0.6b-v3` is a 600-million-parameter multilingual automatic speech recognition (ASR) model designed for high-throughput speech-to-text transcription. It extends the [parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) model by expanding language support from English to 25 European languages. The model automatically detects the language of the audio and transcribes it without requiring additional prompting. It is part of a series of models that leverage the [Granary](https://huggingface.co/datasets/nvidia/Granary) [1, 2] multilingual corpus as their primary training dataset.
+
+🗣️ Try Demo here: https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v3 
+
+**Supported Languages:**  
+Bulgarian (**bg**), Croatian (**hr**), Czech (**cs**), Danish (**da**), Dutch (**nl**), English (**en**), Estonian (**et**), Finnish (**fi**), French (**fr**), German (**de**), Greek (**el**), Hungarian (**hu**), Italian (**it**), Latvian (**lv**), Lithuanian (**lt**), Maltese (**mt**), Polish (**pl**), Portuguese (**pt**), Romanian (**ro**), Slovak (**sk**), Slovenian (**sl**), Spanish (**es**), Swedish (**sv**), Russian (**ru**), Ukrainian (**uk**)
+
+This model is ready for commercial/non-commercial use.