Automatic Speech Recognition
Transformers
Safetensors
voxtral_realtime
mistral
voxtral
voxtral-realtime
asr
quantization
bitsandbytes
int4
nf4
4-bit precision
Instructions to use meghanamakkapati/MistralAI_INT4_quantization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use meghanamakkapati/MistralAI_INT4_quantization with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="meghanamakkapati/MistralAI_INT4_quantization")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("meghanamakkapati/MistralAI_INT4_quantization") model = AutoModelForSpeechSeq2Seq.from_pretrained("meghanamakkapati/MistralAI_INT4_quantization") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "VoxtralRealtimeForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation_function": "gelu", | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "max_position_embeddings": 1500, | |
| "model_type": "voxtral_realtime_encoder", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": 750, | |
| "vocab_size": 131072 | |
| }, | |
| "audio_length_per_tok": 8, | |
| "default_num_delay_tokens": 6, | |
| "downsample_factor": 4, | |
| "dtype": "bfloat16", | |
| "hidden_size": 3072, | |
| "model_type": "voxtral_realtime", | |
| "projector_hidden_act": "gelu", | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 131072, | |
| "model_type": "voxtral_realtime_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": 8192, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "transformers_version": "5.8.0.dev0" | |
| } | |