Add Pascal API for Dolphin CTC models (#2096)

This commit is contained in:
Fangjun Kuang
2025-04-03 16:00:22 +08:00
committed by GitHub
parent 07a5701af6
commit 8137ac9f0b
11 changed files with 343 additions and 7 deletions

View File

@@ -6,7 +6,10 @@ with non-streaming speech recognition models.
|Directory| Description|
|---------|------------|
|[run-vad-with-whisper.sh](./run-vad-with-whisper.sh)|It shows how to use the VAD + Whisper for speech recognition.|
|[run-vad-with-sense-voice.sh](./run-vad-with-sense-voice.sh)|It shows how to use the VAD + SenseVoice for speech recognition.|
|[run-vad-with-dolphin-ctc.sh](./run-vad-with-dolphin-ctc.sh)|It shows how to use the VAD + [Dolphin](https://github.com/DataoceanAI/Dolphin) for speech recognition.|
|[run-vad-with-whisper.sh](./run-vad-with-whisper.sh)|It shows how to use the VAD + [Whisper](https://github.com/openai/whisper) for speech recognition.|
|[run-vad-with-sense-voice.sh](./run-vad-with-sense-voice.sh)|It shows how to use the VAD + [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) for speech recognition.|
|[run-vad-with-moonshine.sh](./run-vad-with-moonshine.sh)|It shows how to use the VAD + [Moonshine](https://github.com/usefulsensors/moonshine) for speech recognition.|
Please refer to [non-streaming-asr](../non-streaming-asr) for more kinds of non-streaming models.