michael-treadgold/speech-nano
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Polish model card and add README banner

Browse Source
This commit is contained in:
Owen Song
2026-06-17 22:07:42 +00:00
committed by system
parent bf70cf4986
commit 833d2ecaa3
22 changed files with 167 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+94 -48
View File
@@ -8,45 +8,30 @@ tags:
- speech-synthesis
- pytorch
- ultra-small
- tiny-tts
- local-tts
- efficient-inference
- experimental
pipeline_tag: text-to-speech
library_name: pytorch
---
<p align="center">
<img src="https://huggingface.co/owensong/Inflect-Nano-v1/resolve/main/assets/inflect-nano-banner.svg" alt="Inflect-Nano-v1 banner" width="100%">
</p>
# Inflect-Nano-v1
Inflect-Nano-v1 is an **ultra-small English text-to-speech model** with only **4.63M inference parameters total**. That includes both the acoustic model and the neural vocoder.
**Inflect-Nano-v1 is a 4.63M-parameter English text-to-speech model, including its neural vocoder.**
The goal is simple: explore how far a truly tiny, fully local TTS stack can be pushed while staying small enough to run in places where normal TTS models are too large. It is one of the smallest neural TTS releases in this class, sitting far below the size of most modern speech synthesis systems.
It is built around one question: how usable can a complete local TTS stack get when the entire inference model is smaller than many single embeddings tables in modern speech systems?
This is an experimental release, not a production or SOTA voice model. It is small, fast to load, and usable for demos, but it still has audible quality limits.
This is not a SOTA voice model. The point is the size-to-functionality ratio: a complete text-to-waveform TTS pipeline that is small enough for tiny local experiments, offline assistants, embedded prototypes, browser/WASM-style work, and efficient inference research.
## Why It Is Notable
<p align="center">
<b>4.632M total params</b> | <b>3.465M acoustic</b> | <b>1.167M vocoder</b> | <b>24 kHz</b> | <b>English</b>
</p>
- **4.63M total inference parameters**
- **Includes the vocoder**, not just a front-end acoustic model
- English-only single-voice speech synthesis
- 24 kHz waveform output
- Compact non-autoregressive acoustic model
- Small Snake-activation HiFi-GAN-style vocoder
- Designed for local/offline experiments and tiny-model research
## Quick Facts
| Item | Value |
|---|---:|
| Total inference parameters | **4.632M** |
| Acoustic model | **3.465M** |
| Vocoder generator | **1.167M** |
| Language | English |
| Voice | single male voice |
| Sample rate | 24 kHz |
| Acoustic output | 80-bin mel spectrogram |
| Vocoder | Snake V2Mid HiFi-GAN-style generator |
## Audio Examples
## Listen First
These examples cover punctuation, short questions, numbers, hard words, longer phrasing, and transition-heavy prompts.
@@ -61,7 +46,41 @@ These examples cover punctuation, short questions, numbers, hard words, longer p
| If Logan sounded uneasy, then it happened near Long Beach, and the pause has to carry that. | <audio controls preload="none" src="https://huggingface.co/owensong/Inflect-Nano-v1/resolve/main/examples/example_07.wav"></audio> |
| The word aluminum should not steal attention from the softer ending after entrepreneur. | <audio controls preload="none" src="https://huggingface.co/owensong/Inflect-Nano-v1/resolve/main/examples/example_08.wav"></audio> |
## Install
## Why This Exists
Most strong TTS models are large. Many "small" TTS demos also depend on a larger external vocoder, which hides a lot of the real inference cost. Inflect-Nano-v1 counts both sides:
```text
text -> acoustic model -> mel spectrogram -> neural vocoder -> waveform
```
The model is intentionally constrained:
| Capability | Inflect-Nano-v1 |
|---|---:|
| Complete text-to-waveform stack | Yes |
| External vocoder required | No |
| Total inference parameters | **4.632M** |
| Sample rate | **24 kHz** |
| Language | English |
| Voice count | 1 |
| Voice cloning | No |
| Multilingual | No |
## Size Context
Approximate parameter comparison:
| Model / class | Params | Relative to Inflect-Nano-v1 |
|---|---:|---:|
| Inflect-Nano-v1 | **4.63M** | 1.0x |
| Kokoro-82M | ~82M | ~17.7x larger |
| Chatterbox-sized TTS | ~500M | ~108x larger |
| Multi-billion TTS systems | 1B+ | 216x+ larger |
The comparison is about model scale, not quality parity. Larger models are expected to sound better.
## Quickstart
```bash
git clone https://huggingface.co/owensong/Inflect-Nano-v1
@@ -69,9 +88,7 @@ cd Inflect-Nano-v1
pip install -r requirements.txt
```
The text frontend may download tokenizer files on first run.
## Usage
Generate audio:
```bash
python inference.py \
@@ -79,7 +96,7 @@ python inference.py \
--out sample.wav
```
CPU example:
CPU:
```bash
python inference.py \
@@ -99,28 +116,45 @@ python inference.py \
--out sample_controlled.wav
```
Gradio demo:
Local Gradio demo:
```bash
python app.py
```
The text frontend may download tokenizer files on first run.
## Model Summary
| Component | Parameters | Notes |
|---|---:|---|
| Acoustic model | **3,465,125** | Compact non-autoregressive FastSpeech-style model |
| Vocoder generator | **1,167,077** | Snake V2Mid HiFi-GAN-style generator |
| Total inference model | **4,632,202** | Acoustic + vocoder |
Model files:
```text
weights/inflect_nano_v1_acoustic.pt
weights/inflect_nano_v1_vocoder.pt
```
## Architecture
Inflect-Nano-v1 is a two-part TTS stack:
```text
text
-> normalization + English G2P frontend
-> compact FastSpeech-style acoustic model
-> 80-bin mel spectrogram
-> Snake V2Mid HiFi-GAN-style vocoder
-> 24 kHz waveform
Text
-> English normalization + G2P frontend
-> Compact FastSpeech-style acoustic model
-> 80-bin mel spectrogram
-> Snake V2Mid HiFi-GAN-style vocoder
-> 24 kHz waveform
```
### Acoustic Model
The acoustic model is a compact non-autoregressive FastSpeech-style network. It predicts duration, energy, brightness, and pitch, expands token states into frame states, and decodes 80-bin mel spectrograms.
The acoustic model predicts duration, energy, brightness, and pitch, expands token states into frame states, and decodes 80-bin mel spectrograms.
Main config:
@@ -156,7 +190,7 @@ heads/embeds/projections: remainder
### Vocoder
The vocoder is a custom Snake-activation HiFi-GAN-style generator.
The vocoder is a custom Snake-activation HiFi-GAN-style generator. Discriminators are training-only and are not included in inference parameter counts.
Main config:
@@ -178,14 +212,25 @@ Main config:
}
```
Discriminators are training-only and are not included in inference parameter counts.
## Intended Use
## Model Files
Good fits:
```text
weights/inflect_nano_v1_acoustic.pt
weights/inflect_nano_v1_vocoder.pt
```
- Tiny local TTS experiments
- Offline assistant prototypes
- Embedded or low-resource speech demos
- Efficient inference research
- Browser/WASM-style exploration
- Baseline for sub-5M TTS work
Poor fits:
- Production narration
- Accessibility-critical output
- Voice cloning
- Multilingual TTS
- High-fidelity studio speech
- Long-form audiobook generation
## Limitations
@@ -194,9 +239,10 @@ This model is intentionally tiny and has clear quality limits:
- Unseen text can stumble or sound unstable.
- The voice can sound robotic, buzzy, or artifacted.
- Long or unusual prompts are less reliable.
- The vocoder is a major quality bottleneck.
- It is not a voice cloning model.
- It is not multilingual.
- It is not suitable for production accessibility, safety, or high-quality narration use.
- It is not suitable for safety-critical or production accessibility use.
## Recommended Framing