Hugging Face's logo

OpenMOSS-Team
/
MOSS-Transcribe-Diarize

Audio-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_transcribe_diarize
text-generation
moss
audio
speech
asr
diarization
timestamp-asr
long-form-audio
multimodal
multilingual
custom_code
Eval Results
Model card Files
xet
 Community
22
zylin12 commited on
Commit
4026375
·
verified ·
1 Parent(s): 4a1af86

Bold language count and audio duration in README

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -28,7 +28,7 @@ pipeline_tag: audio-text-to-text
28
 
29
  MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.
30
 
31
- It supports transcription and diarization across 50+ languages, single-pass inference on audio recordings up to 90 minutes long, and custom hotword prompting for domain-specific terms.
32
 
33
  Given an audio or video file, the model generates a compact speaker-aware transcript in one pass, including timestamps and anonymous speaker labels such as `[S01]`, `[S02]`, and beyond.
34
 
 
28
 
29
  MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.
30
 
31
+ It supports transcription and diarization across **50+** languages, single-pass inference on audio recordings up to **90 minutes** long, and custom hotword prompting for domain-specific terms.
32
 
33
  Given an audio or video file, the model generates a compact speaker-aware transcript in one pass, including timestamps and anonymous speaker labels such as `[S01]`, `[S02]`, and beyond.
34