Skip to content
ModelVerifiedExternal
Download

Qwen3 ForcedAligner 0.6B ONNX

| Field | Value | | Upstream model | Qwen/Qwen3-ForcedAligner-0.6B | | ONNX artifact source | valoomba/Qwen3-ForcedAligner-0.6B-ONNX | | Upstream source revision | c7cbfc2048c462b0d63a45797104fc9db3ad62b7 | | ONNX...

Sourcehuggingface.co/tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX/tree/dfae9e3dfb8a00410d8771158fafb01bac3fe2a5
KindText modelBase modelQwen/Qwen3-ForcedAligner-0.6BVersionQ4Publisher@tonythethompsonCgrade

Model source

Kind
Text model
File size
1,000 MB
Base model
Qwen/Qwen3-ForcedAligner-0.6B
Version
vQ4
Updated
Oct 3, 2026
Publisher
@tonythethompson
Downloads
24
Parameters
6B
Source
Hugging Face

Source description

Qwen3-ForcedAligner-0.6B (Q4 ONNX)

Source

FieldValue
Upstream modelQwen/Qwen3-ForcedAligner-0.6B
ONNX artifact sourcevaloomba/Qwen3-ForcedAligner-0.6B-ONNX
Upstream source revisionc7cbfc2048c462b0d63a45797104fc9db3ad62b7
ONNX artifact source revision261c9ed100c1b18a4a1fbc488e05625dc9a4ae5c
Packaging source revision4b904d4e0eb18c8dd1726ff5e830f72c06dd665b
Export tool/scriptCommunity ONNX export (valoomba) repackaged for checksum-verified distribution
Quantization recipeQ4 ONNX (onnx/model_q4.onnx, self-contained)

Model

  • Architecture: Encoder (24L, d=1024) + 28L decoder body, non-autoregressive
  • Output: Word-level timestamps via slot injection; 5000-class softmax x 80ms resolution
  • Max audio duration: 5 minutes
  • Inference: Single forward pass
  • Languages: 11 (English, Chinese, Cantonese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish)

Architecture and capability figures above are inherited from the upstream / valoomba source and are not independently re-measured here.

Files

FileSizeSHA256
onnx/model_q4.onnx~1000 MB59b528896d70b34e57838e160d16d5f7cfc02d86c7c6ad46cdc57c25c15497b7
config.json——
tokenizer.json——
vocab.json——
merges.txt——
preprocessor_config.json——
tokenizer_config.json——
special_tokens_map.json——
added_tokens.json——

Note: model_q4.onnx is self-contained (no external data sidecar required).

Intended Use

Word-level forced alignment for local inference via ONNX Runtime.

Runtime Notes

  • Designed for ONNX Runtime compatible runtimes.
  • Input: 16 kHz mono audio.
  • Inference: single forward pass, non-autoregressive.
  • Q4 quantization: self-contained ONNX with no external sidecar.

Precision and Packaging

Export tooling, precision, and quantization are recorded in the Source table above. This packaging mirror does not publish independent parity benchmarks; validate on your target execution provider before production use.

Limitations

  • 5-minute maximum audio duration per inference call.
  • Q4 quantization may affect timestamp precision at the margin; validate on representative audio before production use.
  • 11-language coverage; quality by language not benchmarked in this repo.

License

Apache 2.0 — see the original model card. This packaging repo adds no new license terms.

Sources

1 source
Hugging FacePrimaryVersion dfae9e3dfb8a00410d8771158fafb01bac3fe2a5
huggingface.co/tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX/tree/dfae9e3dfb8a00410d8771158fafb01bac3fe2a5

Verified Oct 3

Model artifacts

1 artifact

onnx/model_q4.onnx

onnx · Q4 · 1,000 MB · SHA-256 59b528896d70…97b7 · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX

--- license: apache-2.0 base_model: Qwen/Qwen3-ForcedAligner-0.6B base_model_relation: quantized pipeline_tag: automatic-speech-recognition library_name: onnxruntime language: - en - zh - yue - fr - de - it - ja - ko - pt - ru - es tags: - onnx - onnxruntime - qwen3_asr - forced-alignment - word-level - qwen3 --- # Qwen3-ForcedAligner-0.6B (Q4 ONNX) ## Source | Field | Value | |---|---| | Upstream model | [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B) | | ONNX artifact source | [valoomba/Qwen3-ForcedAligner-0.6B-ONNX](https://huggingface.co/valoomba/Qwen3-ForcedAligner-0.6B-ONNX) | | Upstream source revision | `c7cbfc2048c462b0d63a45797104fc9db3ad62b7` | | ONNX artifact source revision | `261c9ed100c1b18a4a1fbc488e05625dc9a4ae5c` | | Packaging source revision | `4b904d4e0eb18c8dd1726ff5e830f72c06dd665b` | | Export tool/script | Community ONNX export (valoomba) repackaged for checksum-verified distribution | | Quantization recipe | Q4 ONNX (`onnx/model_q4.onnx`, self-contained) | ## Model - **Architecture**: Encoder (24L, d=1024) + 28L decoder body, non-autoregressive - **Output**: Word-level timestamps via slot injection; 5000-class softmax x 80ms resolution - **Max audio duration**: 5 minutes - **Inference**: Single forward pass - **Languages**: 11 (English, Chinese, Cantonese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish) Architecture and capability figures above are inherited from the upstream / valoomba source and are not independently re-measured here. ## Files | File | Size | SHA256 | |---|---|---| | `onnx/model_q4.onnx` | ~1000 MB | `59b528896d70b34e57838e160d16d5f7cfc02d86c7c6ad46cdc57c25c15497b7` | | `config.json` | — | — | | `tokenizer.json` | — | — | | `vocab.json` | — | — | | `merges.txt` | — | — | | `preprocessor_config.json` | — | — | | `tokenizer_config.json` | — | — | | `special_tokens_map.json` | — | — | | `added_tokens.json` | — | — | Note: `model_q4.onnx` is self-contained (no external data sidecar required). ## Intended Use Word-level forced alignment for local inference via ONNX Runtime. ## Runtime Notes - Designed for ONNX Runtime compatible runtimes. - Input: 16 kHz mono audio. - Inference: single forward pass, non-autoregressive. - Q4 quantization: self-contained ONNX with no external sidecar. ## Precis...

NoteOct 3huggingface.co/tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX

Source context: 24 downloads · 0 likes · Pipeline automatic-speech-recognition · Library onnxruntime · Repo tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX

NoteJul 17huggingface.co/tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX

Source context: 51 downloads · 0 likes · Pipeline automatic-speech-recognition · Library onnxruntime · Repo tonythethompson/Qwen3-ForcedAligner-0.6B-ONNX