Update README.md

README.md

@@ -1,199 +1,132 @@
----
-library_name: transformers
-tags: []
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## 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
+# TinyWave Interleaved Expressive 2B
 
-Use the code below to get started with the model.
+**TinyWave Interleaved Expressive 2B** is a compact, expressive speech-to-speech and speech-text language model distilled from the 7B SPIRIT-LM teacher. It supports **interleaved audio and text inputs** and is trained on 50k hours of public data using a multi-level layer-aligned distillation framework.
 
-[More Information Needed]
+Despite being 3× smaller than its teacher, the model retains **93–97%** of its accuracy on expressive benchmarks like StoryCloze and SALMon, and outperforms size-matched baselines. This model is ideal for **real-time multimodal agents**, **spoken dialogue systems**, and **low-resource deployment**.
 
-## Training Details
+> 📖 For more information, see the [TinyWave paper (arXiv:2506.23670)](https://arxiv.org/abs/2506.23670) and [project website](https://mohammadmahdinoori.github.io/tinywave-landing/).
 
-### Training Data
+## 🔧 Usage
 
-<!-- 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. -->
+This model accepts interleaved speech and text inputs. It expects inputs to be encoded using SPIRIT-LM’s **expressive speech tokenizer**.
 
-[More Information Needed]
+### 1. Clone SPIRIT-LM and Install Requirements
 
-### 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
+```bash
+git clone https://github.com/facebookresearch/spiritlm
+cd spiritlm
+pip install -e '.[eval]'
+````
 
+---
 
+### 2. Load Tokenizer
 
-## Model Examination [optional]
+```python
+from spiritlm.speech_tokenizer import spiritlm_expressive
+speech_tokenizer = spiritlm_expressive()
+```
 
-<!-- Relevant interpretability work for the model goes here -->
+---
 
-[More Information Needed]
+### 3. Inference Code
 
-## Environmental Impact
+```python
+from transformers import LlamaForCausalLM, AutoTokenizer
+import torchaudio
+import torch
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+# Load model and tokenizer
+MODEL_PATH = "tinywave/interleaved-expressive-2b"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = LlamaForCausalLM.from_pretrained(MODEL_PATH, device_map="auto", torch_dtype=torch.bfloat16)
 
-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).
+# Audio + Speech tokenizer
+speech_tokenizer = spiritlm_expressive()
 
-- **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]
+def get_inference(input_audio_path):
+    audio, _ = torchaudio.load(input_audio_path)
+    input_values = audio.view(1, 1, -1).to(speech_tokenizer.hubert_model.device).float()
+    string_tokens = speech_tokenizer.encode_string(input_values)
+    input_ids = tokenizer(string_tokens, return_tensors="pt").input_ids.to(model.device)
+    output = model.generate(input_ids, max_new_tokens=256, top_p=0.9, temperature=0.9, do_sample=True)
+    return tokenizer.decode(output[0])
 
-## Technical Specifications [optional]
+# Text-based prompt
+def get_inference_text(prompt):
+    input_ids = tokenizer(prompt + " [Speech]", return_tensors="pt").input_ids.to(model.device)
+    output = model.generate(input_ids, max_new_tokens=256, top_p=0.9, temperature=0.9, do_sample=True)
+    return tokenizer.decode(output[0])
+```
 
-### Model Architecture and Objective
+---
 
-[More Information Needed]
+### 4. Decoding to WAV (optional)
 
-### Compute Infrastructure
+```python
+import numpy as np
+from scipy.io.wavfile import write
 
-[More Information Needed]
+def save_array_to_wav_int16(audio_array: np.ndarray, sampling_rate=16000, filename="output.wav"):
+    scaled = np.int16(audio_array / np.max(np.abs(audio_array)) * 32767)
+    write(filename, sampling_rate, scaled)
 
-#### Hardware
+decoded_audio = speech_tokenizer.decode(output_text.replace(" ", "").replace("<s>", "").replace("</s>", ""), speaker_id=2)
+save_array_to_wav_int16(decoded_audio, filename="generated.wav")
+```
 
-[More Information Needed]
+---
 
-#### Software
+## 🗣️ Inference Examples
 
-[More Information Needed]
+### 🎧 Speech Continuation
 
-## Citation [optional]
+Input: `speech.wav` (spoken sentence)
+Output: Expressive speech continuation in the same style and tone.
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+---
 
-**BibTeX:**
+### 💬 Mixed Input: Text → Speech
 
-[More Information Needed]
+Prompt:
 
-**APA:**
+```
+"Once upon a time in a small village, a mysterious sound echoed through the forest. [Speech]"
+```
 
-[More Information Needed]
+Output: Expressive spoken continuation in WAV format.
 
-## Glossary [optional]
+---
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## 🧠 Model Details
 
-[More Information Needed]
+| Feature             | Description                                       |
+| ------------------- | ------------------------------------------------- |
+| Architecture        | 2B parameter distilled transformer                |
+| Tokenizer           | SPIRIT-LM Expressive (HuBERT + pitch/style)       |
+| Tasks               | Speech continuation, mixed speech-text generation |
+| Teacher Model       | SPIRIT-LM-Expressive 7B                           |
+| Distillation Method | Layer-aligned: hidden states, attention, logits   |
+| Input Types         | Discrete HuBERT tokens and text                   |
 
-## More Information [optional]
+---
 
-[More Information Needed]
+## 📎 Citation
 
-## Model Card Authors [optional]
+```bibtex
+@article{nouriborji2025tinywave,
+  title={Efficient Interleaved Speech Modeling through Knowledge Distillation},
+  author={Nouriborji, Mohammadmahdi and Rohanian, Morteza},
+  journal={arXiv preprint arXiv:2506.23670},
+  year={2025}
+}
+```
 
-[More Information Needed]
+---
 
-## Model Card Contact
+## 📂 Resources
 
-[More Information Needed]
+* 🔗 [Project Page](https://mohammadmahdinoori.github.io/tinywave-landing/)
+* 💬 [Demo Samples](https://mohammadmahdinoori.github.io/tinywave-landing/#samples)
+* 🧠 [Training & Codebase](https://github.com/mohammadmahdinoori/TinyWave)