Update custom model files, README, and requirements

README.md

@@ -1,199 +1,73 @@
 ---
-library_name: transformers
-tags: []
+license: mit
+language:
+- en
+datasets:
+- speechbrain/LoquaciousSet
+base_model:
+- openai/whisper-large-v3-turbo
+- HuggingFaceTB/SmolLM3-3B
+pipeline_tag: automatic-speech-recognition
+tags:
+- asr
+- speech-recognition
+- audio
+- smollm
+- whisper
+- mlp
 ---
 
-# Model Card for Model ID
+# Tiny Audio
 
-<!-- Provide a quick summary of what the model is/does. -->
+A speech recognition model trained in 24 hours on a single GPU for ~$12. Built with the [Tiny Audio](https://github.com/alexkroman/tiny-audio) codebase—a minimal, hackable framework for training ASR models.
 
+## Architecture
 
+```
+Audio (16kHz) → Whisper Encoder (frozen) → MLP Projector (trained) → SmolLM3-3B (frozen) → Text
+```
 
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
+**MLP Projector:**
+- Convolutional downsampling: 4x sequence compression via two stride-2 conv layers
+- Linear (1280 → 2048) → GELU → Linear (2048 → 2048)
+- Output normalization: RMSNorm
 
 ## Training Details
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
+| | |
+|---|---|
+| **Dataset** | LoquaciousSet (25,000 hours) |
+| **Hardware** | Single NVIDIA A40 40GB |
+| **Training Time** | ~24 hours |
+| **Cost** | ~$12 |
+| **Trainable Parameters** | ~12M (projector only) |
 
-**APA:**
+## Performance
 
-[More Information Needed]
+**Word Error Rate (WER): 12.14%** on LoquaciousSet test set.
 
-## Glossary [optional]
+See the [community leaderboard](https://github.com/alexkroman/tiny-audio#leaderboard) for comparisons.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## Usage
 
-[More Information Needed]
+```python
+from transformers import pipeline
 
-## More Information [optional]
+pipe = pipeline("automatic-speech-recognition", model="mazesmazes/tiny-audio", trust_remote_code=True)
 
-[More Information Needed]
+result = pipe("path/to/audio.wav")
+print(result["text"])
+```
 
-## Model Card Authors [optional]
+## Limitations
 
-[More Information Needed]
+- English only
+- Optimized for 16kHz audio; other sample rates are resampled automatically
+- Performance may degrade on heavily accented speech, noisy environments, or domain-specific jargon
+- Maximum audio length limited by context window
 
-## Model Card Contact
+## Learn More
 
-[More Information Needed]
+- **[Train your own model](https://github.com/alexkroman/tiny-audio)** — The full codebase with training scripts
+- **[Free 3-hour course](https://github.com/alexkroman/tiny-audio/blob/main/docs/course/0-course-overview.md)** — Build your own ASR system from scratch
+- **[Submit to leaderboard](https://github.com/alexkroman/tiny-audio#leaderboard)** — Share your trained model

asr_modeling.py

@@ -168,7 +168,7 @@ class ASRModel(PreTrainedModel, GenerationMixin):
         decoder_kwargs = {
             "attn_implementation": config.attn_implementation,
             "trust_remote_code": True,
-            "tie_word_embeddings": False,
+            "tie_word_embeddings": True,
             "low_cpu_mem_usage": True,
             "dtype": dtype,
         }

asr_pipeline.py

@@ -1,3 +1,4 @@
+import re
 from pathlib import Path
 from typing import Any
 
@@ -473,4 +474,6 @@ class ASRPipeline(transformers.AutomaticSpeechRecognitionPipeline):
                 tokens = tokens[0]
 
         text = self.tokenizer.decode(tokens, skip_special_tokens=True).strip()
+        # Strip <think>...</think> tags (Qwen3 doesn't respect /no_think prompt)
+        text = re.sub(r"<think>.*?</think>\s*", "", text, flags=re.DOTALL).strip()
         return {"text": text}

handler.py

@@ -0,0 +1,114 @@
+"""Custom inference handler for HuggingFace Inference Endpoints."""
+
+from typing import Any, Dict, List, Union
+
+import torch
+
+try:
+    # For remote execution, imports are relative
+    from .asr_modeling import ASRModel
+    from .asr_pipeline import ASRPipeline
+except ImportError:
+    # For local execution, imports are not relative
+    from asr_modeling import ASRModel  # type: ignore[no-redef]
+    from asr_pipeline import ASRPipeline  # type: ignore[no-redef]
+
+
+class EndpointHandler:
+    def __init__(self, path: str = ""):
+        import os
+
+        import nltk
+
+        nltk.download("punkt_tab", quiet=True)
+
+        os.environ.setdefault("PYTORCH_CUDA_ALLOC_CONF", "expandable_segments:True")
+
+        # Enable TF32 for faster matmul on Ampere+ GPUs (A100, etc.)
+        # Also beneficial for T4 (Turing) which supports TensorFloat-32
+        torch.backends.cuda.matmul.allow_tf32 = True
+        torch.backends.cudnn.allow_tf32 = True
+
+        # Set device and dtype
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+
+        # Use float16 for better T4 compatibility (bfloat16 not well supported on T4)
+        # T4 has excellent float16 performance with tensor cores
+        self.dtype = torch.float16 if self.device == "cuda" else torch.float32
+
+        # Enable CUDA optimizations
+        if torch.cuda.is_available():
+            torch.backends.cudnn.benchmark = True
+
+        # Prepare model kwargs for pipeline
+        model_kwargs = {
+            "dtype": self.dtype,
+            "low_cpu_mem_usage": True,
+        }
+        if torch.cuda.is_available():
+            model_kwargs["attn_implementation"] = (
+                "flash_attention_2" if self._is_flash_attn_available() else "sdpa"
+            )
+
+        # Load model (this loads the model, tokenizer, and feature extractor)
+        self.model = ASRModel.from_pretrained(path, **model_kwargs)
+
+        # Instantiate custom pipeline - it will get feature_extractor and tokenizer from model
+        self.pipe = ASRPipeline(
+            model=self.model,
+            feature_extractor=self.model.feature_extractor,
+            tokenizer=self.model.tokenizer,
+            device=self.device,
+        )
+
+        # Apply torch.compile if enabled (after model is loaded by pipeline)
+        # Use "default" mode for T4 - better compatibility than "reduce-overhead"
+        # "reduce-overhead" is better for A100+ but can be slower on older GPUs
+        if torch.cuda.is_available() and os.getenv("ENABLE_TORCH_COMPILE", "1") == "1":
+            compile_mode = os.getenv("TORCH_COMPILE_MODE", "default")
+            self.model = torch.compile(self.model, mode=compile_mode)
+            self.pipe.model = self.model
+
+        # Warmup the model to trigger compilation and optimize kernels
+        if torch.cuda.is_available():
+            self._warmup()
+
+    def _is_flash_attn_available(self):
+        """Check if flash attention is available."""
+        import importlib.util
+
+        return importlib.util.find_spec("flash_attn") is not None
+
+    def _warmup(self):
+        """Warmup to trigger model compilation and allocate GPU memory."""
+        try:
+            # Create dummy audio (1 second at config sample rate)
+            sample_rate = self.pipe.model.config.audio_sample_rate
+            dummy_audio = torch.randn(sample_rate, dtype=torch.float32)
+
+            # Run inference to trigger torch.compile and kernel optimization
+            with torch.inference_mode():
+                warmup_tokens = self.pipe.model.config.inference_warmup_tokens
+                _ = self.pipe(
+                    {"raw": dummy_audio, "sampling_rate": sample_rate},
+                    max_new_tokens=warmup_tokens,
+                )
+
+            # Force CUDA synchronization to ensure kernels are compiled
+            if torch.cuda.is_available():
+                torch.cuda.synchronize()
+                # Clear cache after warmup to free memory
+                torch.cuda.empty_cache()
+
+        except Exception as e:
+            print(f"Warmup skipped due to: {e}")
+
+    def __call__(self, data: Dict[str, Any]) -> Union[Dict[str, Any], List[Dict[str, Any]]]:
+        inputs = data.get("inputs")
+        if inputs is None:
+            raise ValueError("Missing 'inputs' in request data")
+
+        # Pass through any parameters from request, let model config provide defaults
+        params = data.get("parameters", {})
+
+        return self.pipe(inputs, **params)

requirements.txt

@@ -0,0 +1,6 @@
+# Core dependencies for tiny-audio model inference
+# This file is pushed to HuggingFace for model repository
+
+# Transformers - main library for model loading and inference
+transformers>=4.57.0
+truecase