| --- |
| license: cc-by-nc-4.0 |
| base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| base_model_relation: finetune |
| datasets: |
| - danielrosehill/Read-Aloud-Voice-Sentences |
| language: |
| - en |
| pipeline_tag: text-to-speech |
| tags: |
| - tts |
| - qwen3-tts |
| - voice-clone |
| - tech-vocabulary |
| - irish-english |
| - fritter |
| extra_gated_prompt: "This is a clone of one real person's voice. Access is by request. CC-BY-NC-4.0: non-commercial use with attribution only. Do not use it to impersonate Daniel Rosehill or to make audio that could be taken as his own words." |
| extra_gated_fields: |
| Name: text |
| Intended use: text |
| "I will use this model non-commercially and will not use it to impersonate the speaker": checkbox |
| --- |
| |
| # Fritter-TTS v1 |
|
|
| A single-speaker text-to-speech fine-tune of [Qwen3-TTS-12Hz-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base) |
| on one voice: Daniel Rosehill, Irish-accented English. It is the text-to-speech side of the |
| [Fritter](https://huggingface.co/danielrosehill/Fritter) line: technical and general English, with AI model names, |
| Linux commands, acronyms and version numbers read the way he reads them. There are no Hebrew words in its training data. |
|
|
| **Licence and access.** CC-BY-NC-4.0: free for non-commercial use with attribution. Access is by request, because this |
| is a clone of a real person's voice. A personal project by Daniel Rosehill; not affiliated with Alibaba Cloud or NVIDIA. |
|
|
| It has not been benchmarked: no listening score or metric is reported here. |
|
|
| ## Listen |
|
|
| Before and after, on the same text. **Before**: the untuned base model, Qwen3-TTS-12Hz-1.7B-Base, cloning the voice from |
| one reference recording. **After**: Fritter-TTS v1. Nothing here was picked by ear. Training takes were at most 15 s, so the |
| longer passages (more than three sentences) are generated sentence by sentence and joined. |
|
|
| | Text | Before | After | |
| |---|---|---| |
| | Restart the Docker container and check the logs again. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/01-short-restart-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/01-short-restart.mp3"></audio> | |
| | I'll SSH into the NAS and see why the backup job failed overnight. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/02-short-ssh-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/02-short-ssh.mp3"></audio> | |
| | The new release needs Python 3.12 and at least 16 GB of RAM. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/03-short-version-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/03-short-version.mp3"></audio> | |
| | The VPN drops whenever the router renews its DHCP lease. I've pinned a static IP for now and opened an issue on GitHub. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/06-medium-network-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/06-medium-network.mp3"></audio> | |
| | The fine-tune ran on an L40S for about an hour. After that I quantized it to Q4_K_M with llama.cpp and pushed the GGUF to Hugging Face. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/05-medium-gpu-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/05-medium-gpu.mp3"></audio> | |
| | I tried Claude Sonnet 4.5, GPT-5 and Gemini 2.5 Pro on the same prompt. Sonnet gave the cleanest JSON, so that's the one going into the pipeline. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/04-medium-models-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/04-medium-models.mp3"></audio> | |
| | The home server runs Ubuntu 24.04 with everything in Docker Compose. Home Assistant, Jellyfin and a small Postgres database each get their own container. Backups go to a Synology NAS every night, and a copy is synced to object storage once a week. It's not glamorous, but it has run for two years with almost no attention. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/07-long-homelab-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/07-long-homelab.mp3"></audio> | |
| | The build failed on CI but worked on my laptop, which is always a bad sign. It turned out the runner was on Node 18 while I was on Node 22. I pinned the version in the workflow file, cleared the npm cache and reran the job. Twenty minutes of debugging for a one-line fix, which is about the usual ratio. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/09-long-debug-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/09-long-debug.mp3"></audio> | |
| | My dictation setup uses a fine-tuned Parakeet model running locally on the GPU. I press a key on the macro pad, speak, and the text lands wherever the cursor is. The fine-tune fixed most of the technical vocabulary, things like Kubernetes, PyTorch and OpenRouter. Numbers were the last thing to sort out, so now I record version numbers the way I actually say them. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/08-long-asr-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/08-long-asr.mp3"></audio> | |
| | Most of my day now involves working alongside AI agents in the terminal. I describe what I want, the agent reads the repository, proposes a change and runs the tests. The trick is giving it enough context without burying it in detail. A short CLAUDE.md file with the project's rules does more than a long prompt ever did. When something goes wrong, I ask it to write down what it learned, so the next session starts smarter. It's not perfect, but it has changed how much I can get done in an afternoon. And I dictate almost all of it, which is why the speech models matter so much to me. | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/10-extended-agents-base.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples/resolve/main/release/10-extended-agents.mp3"></audio> | |
|
|
| More on the public samples page, **[Fritter-ASR/Fritter-TTS-Samples](https://huggingface.co/spaces/Fritter-ASR/Fritter-TTS-Samples)**: every line from the release run |
| next to Daniel's real recordings, and longer passages generated in one pass. |
|
|
| ## How it was made |
|
|
| 1. **Screening.** Daniel's own speech-to-text recording takes (read sentences, recorded on a desktop microphone and his |
| phone), screened for quality: sound events tagged with PANNs, quality scored with DNSMOS, noisy rooms left out. |
| Sentences with Hebrew words were left out. Takes with digits were kept, so the model learns his readings of numbers |
| and versions. |
| 2. **Enhancement.** Every take went through NVIDIA NemotronLabs |
| [RE-USE](https://huggingface.co/nvidia/NVIDIA-NemotronLabs-RE-USE) (OpenMDW-1.1), run as the |
| [`audio-cpp/RE-USE-GGUF`](https://huggingface.co/audio-cpp/RE-USE-GGUF) build through audio.cpp, then a podcast voice |
| chain (EQ, de-ess, 2:1 compression, -20 LUFS), resampled to 24 kHz. |
| 3. **Training.** A full fine-tune (SFT) from the base model, the first run of this line. |
|
|
| ## Training |
|
|
| | | | |
| |---|---| |
| | Data | 9,125 takes of at most 15 s, about 743 min (12.4 h) after trimming: 8,424 speech-to-text takes from [`danielrosehill/Read-Aloud-Voice-Sentences`](https://huggingface.co/datasets/danielrosehill/Read-Aloud-Voice-Sentences) (tech about 450 min, general English about 320 min before the length cap) and 731 read TTS takes without Hebrew words | |
| | Method | Full SFT, upstream `finetuning/sft_12hz.py` with fixes (label shift, sub-talker, `text_projection` applied in training), fp32 master weights with bf16 autocast | |
| | Schedule | LR 7e-6, 3 epochs, batch 2 x grad. accumulation 4, final checkpoint | |
| | Hardware | 1 x L40S (Modal) | |
|
|
| ## Usage |
|
|
| The speaker name is `daniel`. |
|
|
| ```python |
| import torch, soundfile as sf |
| from qwen_tts import Qwen3TTSModel |
| |
| tts = Qwen3TTSModel.from_pretrained("Fritter-ASR/Fritter-TTS", device_map="cuda:0", dtype=torch.bfloat16) |
| wavs, sr = tts.generate_custom_voice(text="Pull the latest image, then restart the container with Docker Compose.", |
| speaker="daniel", language="English") |
| sf.write("out.wav", wavs[0], sr) |
| ``` |
|
|
| Requires `qwen-tts` (tested with 0.1.1). The repo is gated: log in with a token that has access. |
|
|
| **On-device (GGUF).** Q8_0 and Q4_K_M builds for [qwentts.cpp](https://github.com/ServeurpersoCom/qwentts.cpp) (CPU, Android, |
| Vulkan) are in [`Fritter-ASR/Fritter-TTS-GGUF`](https://huggingface.co/Fritter-ASR/Fritter-TTS-GGUF), same speaker `daniel`. |
| |
| ## Version history |
| |
| | Version | Date | Data | Repo | |
| |---|---|---|---| |
| | Fritter-TTS v1 | 2026-11-09 | 9,125 takes, about 743 min, RE-USE-enhanced | this repo | |
| |
| ## Base model and licence notices |
| |
| This model is a fine-tune of [`Qwen/Qwen3-TTS-12Hz-1.7B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base), |
| Copyright 2026 Alibaba Cloud, licensed under [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) (text in |
| `LICENSE-Qwen-Apache-2.0`). It was modified by fine-tuning. The CC-BY-NC-4.0 licence above covers the fine-tune; the |
| base model's licence keeps applying to the base model. |
| |
