Initial upload: Q4 fp16 voxtral realtime

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,99 @@
+---
+base_model: mistralai/Voxtral-Mini-4B-Realtime-2602
+language:
+  - ar
+  - de
+  - en
+  - es
+  - fr
+  - hi
+  - it
+  - nl
+  - pt
+  - zh
+  - ja
+  - ko
+  - ru
+library_name: mlx
+license: apache-2.0
+pipeline_tag: automatic-speech-recognition
+tags:
+  - mlx
+  - mlx-audio
+  - speech-to-text
+  - streaming
+  - realtime
+  - voxtral
+  - fp16
+---
+
+# Voxtral Mini 4B Realtime 4bit (float16)
+
+This is a **4-bit quantized, float16-base** [MLX](https://github.com/ml-explore/mlx) conversion of [mistralai/Voxtral-Mini-4B-Realtime-2602](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602).
+
+## Which variant should you pick?
+
+| Chip           | Recommended                                                                                            | Why                                                                                                                      |
+|----------------|--------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------|
+| **M1 / M2**    | **This repo (`-4bit-fp16`)**                                                                           | Metal on M1/M2 has no native `bfloat16` ALU; bf16 ops fall back to a slower path. `float16` stays on the fast GPU path.  |
+| **M3 / M4+**   | [`iris-sfg/Voxtral-Mini-4B-Realtime-2602-4bit`](https://huggingface.co/iris-sfg/Voxtral-Mini-4B-Realtime-2602-4bit) (bf16) | bf16 is natively supported and gives the same speed as fp16 with a wider dynamic range (slightly safer numerics).       |
+
+Only the non-quantized weights differ between the two repos (norms, biases, scales, some embeddings). The quantized mat-mul weights are bit-identical. Transcription output is byte-identical on a 20 s French clip at temperature 0 (verified locally).
+
+## Conversion
+
+Source model:
+
+- `mistralai/Voxtral-Mini-4B-Realtime-2602`
+
+Local conversion command:
+
+```bash
+python -m mlx_audio.convert \
+  --hf-path mistralai/Voxtral-Mini-4B-Realtime-2602 \
+  --mlx-path /path/to/Voxtral-Mini-4B-Realtime-2602-4bit-fp16 \
+  --quantize \
+  --q-group-size 64 \
+  --q-bits 4 \
+  --dtype float16 \
+  --model-domain stt
+```
+
+Quantization config:
+
+- bits: `4`
+- group size: `64`
+- mode: `affine`
+- non-quant dtype: `float16`
+
+## Files
+
+Only the MLX runtime artifacts needed for inference:
+
+- `model.safetensors`
+- `model.safetensors.index.json`
+- `config.json`
+- `generation_config.json`
+- `params.json`
+- `processor_config.json`
+- `tekken.json`
+
+## Usage
+
+```bash
+pip install "mlx-audio[stt]"
+```
+
+```python
+from mlx_audio.stt.utils import load_model
+
+model = load_model("iris-sfg/Voxtral-Mini-4B-Realtime-2602-4bit-fp16")
+result = model.generate("audio.wav")
+print(result.text)
+```
+
+## Notes
+
+- Base model license remains Apache 2.0.
+- On M3/M4, prefer the `-4bit` (bf16) repo; there is no speed benefit to fp16 there and bf16's wider exponent range is slightly more robust.
+- Transcription quality was verified identical to the bf16 variant at `temperature=0` on a 20 s French parliamentary audio clip.

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "VoxtralRealtimeForConditionalGeneration"
+  ],
+  "audio_config": {
+    "activation_function": "gelu",
+    "attention_dropout": 0.0,
+    "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_key_value_heads": 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": "float16",
+  "hidden_size": 3072,
+  "model_type": "voxtral_realtime",
+  "projector_hidden_act": "gelu",
+  "quantization": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "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": "5.2.0.dev0"
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 11,
+  "transformers_version": "5.2.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea4e642801c525a8b8f4d2ac4ee4685e649502e09b4cfa843fa819ced0be0f5
+size 2507662237

params.json

@@ -0,0 +1,55 @@
+{
+  "dim": 3072,
+  "n_layers": 26,
+  "head_dim": 128,
+  "hidden_dim": 9216,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "use_biases": false,
+  "causal": true,
+  "rope_theta": 1000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072,
+  "model_parallel": 1,
+  "tied_embeddings": true,
+  "sliding_window": 8192,
+  "model_max_length": 131072,
+  "multimodal": {
+    "whisper_model_args": {
+      "encoder_args": {
+        "audio_encoding_args": {
+          "sampling_rate": 16000,
+          "frame_rate": 12.5,
+          "num_mel_bins": 128,
+          "hop_length": 160,
+          "window_size": 400,
+          "chunk_length_s": null,
+          "global_log_mel_max": 1.5,
+          "transcription_format": "streaming"
+        },
+        "dim": 1280,
+        "n_layers": 32,
+        "head_dim": 64,
+        "hidden_dim": 5120,
+        "n_heads": 32,
+        "vocab_size": 131072,
+        "n_kv_heads": 32,
+        "use_biases": true,
+        "use_cache": false,
+        "rope_theta": 1000000.0,
+        "causal": true,
+        "norm_eps": 1e-05,
+        "pos_embed": "rope",
+        "max_source_positions": null,
+        "ffn_type": "swiglu",
+        "norm_type": "rms_norm",
+        "sliding_window": 750
+      },
+      "downsample_args": {
+        "downsample_factor": 4
+      }
+    }
+  },
+  "ada_rms_norm_t_cond": true,
+  "ada_rms_norm_t_cond_dim": 32
+}

processor_config.json

@@ -0,0 +1,15 @@
+{
+  "feature_extractor": {
+    "feature_extractor_type": "VoxtralRealtimeFeatureExtractor",
+    "feature_size": 128,
+    "global_log_mel_max": 1.5,
+    "hop_length": 160,
+    "n_fft": 400,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": true,
+    "sampling_rate": 16000,
+    "win_length": 400
+  },
+  "processor_class": "VoxtralRealtimeProcessor"
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8434af1d39eba99f0ef46cf1450bf1a63fa941a26933a1ef5dbbf4adf0d00e44
+size 14910348