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
Instructions to use OpenMOSS-Team/MOSS-Transcribe-Diarize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-Transcribe-Diarize with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/MOSS-Transcribe-Diarize", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "MossTranscribeDiarizeForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_moss_transcribe_diarize.MossTranscribeDiarizeConfig", | |
| "AutoModel": "modeling_moss_transcribe_diarize.MossTranscribeDiarizeModel", | |
| "AutoModelForCausalLM": "modeling_moss_transcribe_diarize.MossTranscribeDiarizeForConditionalGeneration", | |
| "AutoProcessor": "processing_moss_transcribe_diarize.MossTranscribeDiarizeProcessor" | |
| }, | |
| "model_type": "moss_transcribe_diarize", | |
| "dtype": "bfloat16", | |
| "text_config": { | |
| "model_type": "qwen3", | |
| "vocab_size": 151936, | |
| "hidden_size": 1024, | |
| "intermediate_size": 3072, | |
| "num_hidden_layers": 28, | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "max_position_embeddings": 131072, | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": true, | |
| "rope_theta": 1000000, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "pad_token_id": 151643, | |
| "bos_token_id": null, | |
| "eos_token_id": null | |
| }, | |
| "audio_config": { | |
| "model_type": "whisper", | |
| "num_mel_bins": 80, | |
| "d_model": 1024, | |
| "encoder_layers": 24, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "max_source_positions": 1500, | |
| "dropout": 0.0, | |
| "attention_dropout": 0.0, | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "encoder_layerdrop": 0.0, | |
| "scale_embedding": false | |
| }, | |
| "audio_token_id": 151671, | |
| "audio_merge_size": 4, | |
| "adaptor_input_dim": 4096, | |
| "tie_word_embeddings": true, | |
| "pad_token_id": 151643 | |
| } | |