Duplicate from mouddane/granite-speech-4.1-2b-nar-mlx

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+multilingual_sample.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+library_name: mlx
+license: apache-2.0
+base_model: ibm-granite/granite-speech-4.1-2b-nar
+language: [en, fr, de, es, pt]
+pipeline_tag: automatic-speech-recognition
+tags:
+  - mlx
+  - mlx-audio
+  - speech-to-text
+  - non-autoregressive
+  - granite
+---
+
+# Granite Speech 4.1 2B NAR — MLX
+
+MLX port of [`ibm-granite/granite-speech-4.1-2b-nar`](https://huggingface.co/ibm-granite/granite-speech-4.1-2b-nar) for Apple Silicon. Runs via [mlx-audio](https://github.com/Blaizzy/mlx-audio).
+
+## Architecture
+
+Non-autoregressive ASR via CTC + bidirectional LM editing:
+
+1. **16-layer Conformer encoder** (543M params) produces an initial BPE CTC hypothesis.
+2. **2-layer windowed Q-Former projector** (80M params) converts multi-layer encoder states into audio embeddings.
+3. **40-layer bidirectional Granite editor** (1.6B params) takes `[audio | hypothesis_tokens]` and emits edited logits in a single forward pass — no autoregression, no KV cache.
+4. Final CTC collapse on text-position logits yields the transcript.
+
+Total: ~2.25B params, bf16.
+
+## Quickstart
+
+```python
+from pathlib import Path
+from mlx_audio.stt.utils import load_model
+
+model = load_model(Path("mlx-community/granite-speech-4.1-2b-nar-mlx"))
+out = model.generate("audio.wav")
+print(out.text)
+```
+
+## Limitations
+
+- Batch size 1.
+- bf16 baseline only — no quantized variants yet.
+- No streaming inference.
+- macOS 14+, Apple Silicon.
+
+## Reference
+
+Upstream model card: https://huggingface.co/ibm-granite/granite-speech-4.1-2b-nar
+
+Validated against the upstream PyTorch reference: exact 44-token match and exact transcript string on the example wav.
+
+## License
+
+Apache-2.0, matching the upstream model.

chat_template.jinja

@@ -0,0 +1,118 @@
+{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>'  %}
+{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
+{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
+{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
+{%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
+{%- if available_tools is defined and available_tools %}
+    {%- set tools = available_tools %}
+{%- endif %}
+{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
+                       documents_system_message=documents_system_message_prefix,
+                       default_system_message=g4_default_system_message,
+                       system_message=''
+                       ) %}
+{%- if tools %}
+    {%- for tool in tools %}
+        {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
+    {%- endfor %}
+    {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
+{%- else %}
+    {%- set ns.tools_system_message = '' %}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
+    {%- endfor %}
+    {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
+{%- else %}
+    {%- set ns.documents_system_message = '' %}
+{%- endif %}
+{%- if messages[0].role == 'system' %}
+    {%- if messages[0].content is string %}
+        {%- set ns.system_message = messages[0].content %}
+    {%- elif messages[0].content is iterable %}
+        {%- for entry in messages[0].content %}
+            {%- if entry.type== 'text' %}
+                {%- if ns.system_message != '' %}
+                    {%- set ns.system_message = ns.system_message + '\n' %}
+                {%- endif %}
+                {%- set ns.system_message = ns.system_message + entry.text %}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' +  ns.tools_system_message + '\n\n' + ns.documents_system_message %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
+    {%- endif %}
+{%- else %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message  %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.documents_system_message %}
+    {%- endif %}
+{%- endif %}
+{%- if ns.system_message %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
+{%- else %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = namespace(val='') %}
+    {%- if message.content is string %}
+        {%- set content.val = message.content %}
+    {%- else %}
+        {%- if message.content is iterable %}
+            {%- for entry in message.content %}
+                {%- if entry.type== 'text' %}
+                    {%- if content.val != '' %}
+                        {%- set content.val = content.val + '\n' %}
+                    {%- endif %}
+                    {%- set content.val = content.val + entry.text %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content.val) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|end_of_text|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
+            {{- '<|start_of_role|>user<|end_of_role|>' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content.val }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
+            {{- '<|end_of_text|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_of_role|>assistant<|end_of_role|>' }}
+{%- endif %}

config.json

@@ -0,0 +1,94 @@
+{
+  "architectures": [
+    "GraniteSpeechNarForASR"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_granite_speech_nar.GraniteSpeechNarConfig",
+    "AutoFeatureExtractor": "feature_extraction_granite_speech_nar.GraniteSpeechNarFeatureExtractor",
+    "AutoModel": "modeling_granite_speech_nar.GraniteSpeechNarForASR",
+    "AutoProcessor": "processing_granite_speech_nar.GraniteSpeechNarProcessor"
+  },
+  "blank_token_id": 100257,
+  "ce_loss_lambda": 0.02,
+  "dtype": "bfloat16",
+  "encoder_config": {
+    "blank_token_id": 100257,
+    "bpe_output_dim": 100352,
+    "bpe_pooling_window": 4,
+    "context_size": 200,
+    "conv_expansion_factor": 2,
+    "conv_kernel_size": 15,
+    "dim_head": 128,
+    "dropout": 0.1,
+    "feedforward_mult": 4,
+    "hidden_dim": 1024,
+    "initializer_range": 0.02,
+    "input_dim": 160,
+    "max_pos_emb": 512,
+    "model_type": "granite_speech_nar_encoder",
+    "num_heads": 8,
+    "num_layers": 16,
+    "output_dim": 348,
+    "pred_dropout": 0.25,
+    "self_conditioning_layer": 8
+  },
+  "encoder_ctc_loss_lambda": 0.8,
+  "encoder_layer_indices": [
+    4,
+    8,
+    12,
+    -1
+  ],
+  "min_edit_sequence_length": 8,
+  "model_type": "granite_speech_nar",
+  "projector_config": {
+    "attn_bias": true,
+    "block_size": 15,
+    "downsample_rate": 5,
+    "dropout_prob": 0.1,
+    "encoder_dim": 1024,
+    "hidden_size": 2048,
+    "layernorm_eps": 1e-06,
+    "llm_dim": 2048,
+    "mlp_bias": true,
+    "mlp_ratio": 2,
+    "model_type": "granite_speech_nar_projector",
+    "num_encoder_layers": 4,
+    "num_heads": 32,
+    "num_layers": 2
+  },
+  "scale_projected_embeddings": true,
+  "text_config": {
+    "_name_or_path": "ibm-granite/granite-4.0-1b-base",
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_multiplier": 0.0078125,
+    "bos_token_id": 100257,
+    "dtype": "bfloat16",
+    "embedding_multiplier": 12,
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.1,
+    "intermediate_size": 4096,
+    "logits_scaling": 8,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "granite",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 4,
+    "pad_token_id": 100256,
+    "residual_multiplier": 0.22,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 100352
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.0.dev0"
+}

generation_config.json

@@ -0,0 +1,3 @@
+{
+  "transformers_version": "5.8.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ec4215196eaa20c7b816c0526b3012dfb9b0078e545c9ecdb09c601a6c4992
+size 4509376040

multilingual_sample.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d243650809c1274141ec20ff23045315eaf27567694002ea3ef390048b7058
+size 1596240

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "auto_map": {
+    "AutoFeatureExtractor": "feature_extraction_granite_speech_nar.GraniteSpeechNarFeatureExtractor"
+  },
+  "feature_extractor_type": "GraniteSpeechNarFeatureExtractor",
+  "hop_length": 160,
+  "n_fft": 512,
+  "n_mels": 80,
+  "sampling_rate": 16000,
+  "win_length": 400
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "processor_class": "GraniteSpeechNarProcessor",
+  "auto_map": {
+    "AutoProcessor": "processing_granite_speech_nar.GraniteSpeechNarProcessor"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}