Nemotron 3.5 Asr Streaming 0.6b

--- license: other license_name: openmdw-1.1 license_link: >- https://openmdw.ai/license/1-1/ library_name: nemo language: - en - es - de - fr - it - ar - ja - ko - pt - ru - hi - zh - vi - he - nl - cs - da - pl - 'no' - sv - th - tr - bg - el - et - fi - hr - hu - lt - lv - ro - sk - uk - mt - sl datasets: - nvidia/Granary - multilingual_librispeech - fleurs - mozilla-foundation/common_voice_8_0 - voxpopuli - europarl thumbnail: null tags: - transformers - speech-recognition - cache-aware ASR - automatic-speech-recognition - streaming-asr - multilingual - speech - audio - FastConformer - RNNT - Parakeet - ASR - pytorch - NeMo 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: nemotron-asr-streaming-multilingual-0.6b results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: FLEURS (English) type: google/fleurs config: en_us split: test metrics: - name: WER (1.12s frame size, LangID) type: wer value: 7.91 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: FLEURS (Spanish) type: google/fleurs config: es_419 split: test metrics: - name: WER (1.12s frame size, LangID) type: wer value: 4.11 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: FLEURS (French) type: google/fleurs config: fr_fr split: test metrics: - name: WER (1.12s frame size, LangID) type: wer value: 9.03 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: FLEURS (Italian) type: google/fleurs config: it_it split: test metrics: - name: WER (1.12s frame size, LangID) type: wer value: 4.25 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: FLEURS (Portuguese) type: google/fleurs config: pt_br split: test metrics: - name: WER (1.12s frame size, LangID) type: wer value: 5.48 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: FLEURS (German) type: google/fleurs config: de_de split: test metrics: - name: WER (1.12s frame size, LangID) type: wer value: 8.31 - task: name: Automatic Speech Recogni...

Source context: 49 downloads · 0 likes · Pipeline automatic-speech-recognition · Library nemo · Repo BasedBoba2/nemotron-3.5-asr-streaming-0.6b