Google Chirp 2 vs NVIDIA Nemotron 3.5 Transcribe
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner. Nemotron 3.5 Transcribe doesn't support streaming, so it is not shown.
- Chirp 22.59% · 568ms
- Nemotron 3.5 Transcribe1.89%
NVIDIA Nemotron 3.5 Transcribe is ahead of Google Chirp 2 on both datasets together and the Pipecat Dataset. The Ocular Dataset is too close to call. Google Chirp 2 has a newer release: Google Chirp 3 vs NVIDIA Nemotron 3.5 Transcribe.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.01%2.28%
- Pipecat Dataset WER2.59%1.89%
- Ocular Dataset WER3.80%3.03%
- Time to first text4.50sn/a
- Final-text delay568msn/a
Lower is better on every measure. Too close to call means the likely ranges overlap.
Chirp 2 vs Nemotron 3.5 Transcribe FAQ
Which is more accurate, Google Chirp 2 or NVIDIA Nemotron 3.5 Transcribe?
NVIDIA Nemotron 3.5 Transcribe is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and NVIDIA Nemotron 3.5 Transcribe 2.28%, so NVIDIA Nemotron 3.5 Transcribe makes fewer errors by 0.73 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and NVIDIA Nemotron 3.5 Transcribe 1.89%, so NVIDIA Nemotron 3.5 Transcribe makes fewer errors by 0.70 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
NVIDIA Nemotron 3.5 Transcribe is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and NVIDIA Nemotron 3.5 Transcribe 2.28%, so NVIDIA Nemotron 3.5 Transcribe makes fewer errors by 0.73 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and NVIDIA Nemotron 3.5 Transcribe 1.89%, so NVIDIA Nemotron 3.5 Transcribe makes fewer errors by 0.70 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
They cannot be compared on speed. NVIDIA Nemotron 3.5 Transcribe was tested on whole recordings rather than a live stream, so its speed is not measured.
NVIDIA Nemotron 3.5 Transcribe makes fewer errors on real conversations. NVIDIA Nemotron 3.5 Transcribe was tested on whole recordings rather than a live stream, so its speed is not measured. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
NVIDIA Nemotron 3.5 Transcribe was tested on whole recordings rather than a live stream, so whether it streams partial text was not measured. Google Chirp 2 returns partial text before the speaker stops.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.