nvidia
/

stt_it_conformer_transducer_large

Automatic Speech Recognition

hf-asr-leaderboard

Model card Files Files and versions Community

igitman commited on Oct 25, 2022

Commit

3a5de75

•

1 Parent(s): 3ba4e03

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -185,9 +185,9 @@ All the models in this collection are trained on a composite dataset (NeMo ASRSE
 The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
-| Version | Tokenizer             | Vocabulary Size | MCV 11.0 Dev | MCV 11.0 Test | MLS Dev | MLS Test | VoxPopuli Dev | VoxPopuli Test | Train Dataset   |
-|---------|-----------------------|-----------------|--------------|---------------|---------|----------|---------------|----------------|-----------------|
-| 1.13.0  | SentencePiece Unigram | 1024            | 4.80         | 5.24          | 14.62   | 12.18    | 12.00         | 15.15          | NeMo ASRSET 2.0 |
 ## Limitations
 Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.

 The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
+| Version | Tokenizer             | Vocabulary Size | MCV 11.0 Dev | MCV 11.0 Test | MLS Dev | MLS Test | VoxPopuli Dev | VoxPopuli Test | Train Dataset      |
+|---------|-----------------------|-----------------|--------------|---------------|---------|----------|---------------|----------------|--------------------|
+| 1.13.0  | SentencePiece Unigram | 1024            | 4.80         | 5.24          | 14.62   | 12.18    | 12.00         | 15.15          | NeMo ASRSET It 2.0 |
 ## Limitations
 Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.