speechllm

There are 2 repositories under speechllm topic.

modelscope / FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
audio-visual-speech-recognition conformer dfsmn paraformer pretrained-model punctuation pytorch rnnt speaker-diarization speech-recognition speechgpt speechllm vad voice-activity-detection whisper
Language:Python 13424
FireRedTeam / FireRedASR
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
asr automatic-speech-recognition conformer industrial-grade llm multimodal-llm open-source speech-recognition speechllm transformer
Language:Python 1584
aidayang / FunASR-OneClick
FunASR实时语音识别版，识别麦克风和电脑内播放的声音，电脑语音打字软件
audio-visual-speech-recognition conformer dfsmn funasr paraformer pretrained-models punctuation pytorch rnnt speaker-diarization speech-recognition speechgpt speechllm vad voice-activity-detection whisper
12
PigeonDan1 / ps-slm
TASU: A New Style of Alignment of Speech LLM with only Text Training Data, zero-shot on ASR and Other SU tasks
asr speech-understanding speechllm
Language:Python 4
Nexdata-AI / 1500-Hours-French-Canada-Real-world-Casual-Conversation-and-Monologue-speech-dataset
asr speech-to-text speechllm
Nexdata-AI / 2000-Hours-English-Australia-Real-world-Casual-Conversation-and-Monologue-speech-dataset
asr-model speech-recognition speechllm
Nexdata-AI / 300-Hours-English-India-Spontaneous-Dialogue-Smartphone-speech-dataset
asr-model indian-english speechllm
Nexdata-AI / 556-Hours-Dutch-Real-world-Casual-Conversation-and-Monologue-speech-dataset
asr speech-to-text speechllm
SALT-Research / SHALLOW
SHALLOW, the first hallucination benchmark for ASR models
asr benchmark hallucination shallow speech-recognition speechllm speech-foundation-models speech-evaluation
Language:Python