Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model

Sahil Mahendrakar

Published

Oct 5, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

15% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 5, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

Background context only.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher. It has 10x fewer parameters and needs 15x less compute. We first synthesize a corpus with the teacher and keep its durations, pitch, energy and phoneme features. We then train a small text side to predict these values, and a small decoder to turn the teacher's saved values into the teacher's audio, first with spectral losses and then adversarially. Finally, we connect the two halves and quantize the weights to int8. It needs no alignment learning and no joint training, and it runs on one laptop. Stored in int8, Paradee is 8.5 MB, runs 25x faster than real time on one CPU thread, and scores 4.41 on UTMOS against the teacher's 4.52. The student initially kept a slight buzz, which we trace to the phase of voiced speech between 2 and 8 kHz. A phase-locking filter applied after synthesis removes most of it, with no training and no extra parameters. Code, model files and audio samples are at https://github.com/sahilmahendrakar/paradee

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them.
  • Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher.
  • It has 10x fewer parameters and needs 15x less compute.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them.
  • Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher.
  • It has 10x fewer parameters and needs 15x less compute.

Why it matters for eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.