ampixa/pruned-swar

text-to-speech model by ampixa

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

A smaller, faster Swar, a Nepali voice-cloning TTS model built on F5-TTS. We removed 6 of Swar's 22 transformer blocks and trained the remaining 16 on Nepali speech to recover. Real-time factor is generation time divided by audio length, so lower is faster. At 0.329, one minute of speech takes about 20 seconds to generate. Setup: minimum length, seed 0. load. is therefore the same in wall time and in RTF. Trade-off: pruning costs some accuracy. On our 80-item Nepali dev set, long-text CER is 8.6% against…

ampixa/pruned-swar on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-22T07:22:32.390Z

Inside the original model card — Document outline
  1. Pruned Swar
  2. Speed
  3. Use
  4. Files
  5. Licence and credits

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: cc-by-sa-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

ampixa/pruned-swar is a text-to-speech model repository published by ampixa on Hugging Face. The source reports the f5-tts library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
text-to-speech
Library
f5-tts
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
248,936,580
Architecture
Not reported
License
cc-by-sa-4.0
Access
Not gated by Hugging Face
Created
2026-11-22T06:58:40.000Z
Last modified
2026-11-22T06:58:59.000Z

Compatibility and lineage

Reported languages: ne

Reported base models: Aarjan/swar

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

hexgrad/Kokoro-82M

audio-cpp/audio.cpp-gguf

coqui/XTTS-v2

k2-fsa/OmniVoice

ResembleAI/chatterbox

pnnbao-ump/VieNeu-TTS-v3-Turbo