---
license: gpl-2.0
language_bcp47:
  - hy-AM
  - nan-TW
  - pa-IN
  - sv-SE
  - zh-CN
language:
  - hy
  - nan
  - pa
  - sv
  - zh
  - af
  - am
  - ar
  - as
  - az
  - ba
  - be
  - bg
  - bn
  - ca
  - cs
  - da
  - de
  - el
  - en
  - eo
  - es
  - et
  - eu
  - fa
  - fi
  - fr
  - gl
  - gn
  - he
  - hi
  - ht
  - hu
  - ia
  - id
  - is
  - it
  - ja
  - kk
  - ko
  - ky
  - lo
  - lt
  - ltg
  - mk
  - ml
  - mn
  - mr
  - mt
  - nl
  - pl
  - ps
  - pt
  - ro
  - ru
  - sd
  - sk
  - sl
  - sq
  - sw
  - ta
  - te
  - th
  - tk
  - tn
  - tr
  - tt
  - ug
  - uk
  - ur
  - uz
  - vi
  - yue
  - zu
pipeline_tag: automatic-speech-recognition
tags:
- whipstr
- stt
- asr
---
# Neurlang Whipstr STT (ASR)

A deep learning automatic speech recognition (ASR) system for transcribing speech audio into IPA text using transformer-based sequence-to-sequence models.

- **Language:** Universal (IPA), 74+ languages
- **Model Github:** neurlang/whipstr [https://github.com/neurlang/whipstr](https://github.com/neurlang/whipstr)
- **Model Dataset:** Common Voice 21
- **Model-Native Sample Rates:** 8000 Hz, 16000 Hz, 24000 Hz, 32000 Hz, 48000 Hz
- **Degraded-Performance Sample Rates:** 11025 Hz, 22050 Hz, 44100 Hz
- **License:** GPL v2
- **Release:** 2026-07-09
- **Size:** 642 MB
- **Total parameters:**
   - **Encoder:** 7 237 024
   - **Transformer:** 44 499 744
   - **Total:** 51 736 768
- **CER:** 33.88% (66.12% success rate)
   -  **Note:** Averaged across all supported languages, works better on higher resource languages
- **WER:** 73.00% (27% success rate)
   -  **Note:** Averaged across all supported languages, works better on higher resource languages
- **Training Details:**
   -  **Hardware:** Nvidia Spark
   -  **Batch size:** 1
   -  **Samples:** 1185000
   -  **Duration:** 2:03:23:00
   -  **Runs:** Jul  7 07:43 - Jul  9 11:06 (shut down at Jul  9 12:55)

---

## Inference code

```bash
git clone https://github.com/neurlang/whipstr.git
cd whipstr/
uv run --with torch --with transformers --with phase-spectrogram stt_infer_hf.py --audio /home/m/Downloads/LJ001-0001.wav --model neurlang/ipa-whipstr-medium-48khz-cv-21
```
## Inference code (microphone)

```bash
uv run --with torch --with transformers --with phase-spectrogram --with sounddevice stt_mic_hf.py --model neurlang/ipa-whipstr-medium-48khz-cv-21
```

### Output:


```bash
config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 368/368 [00:00<00:00, 2.09MB/s]
model.safetensors: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 227M/227M [00:07<00:00, 29.4MB/s]
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 199/199 [00:00<00:00, 16263.01it/s]
model.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3.84k/3.84k [00:00<00:00, 12.3MB/s]
Transcription: ˈɪt gˈɪt sˈʌbkəldz dˈɑɹk fˈeɪz fˈæst ðə ɹˌɛpətˈɪʃən luːp nˈoʊ ˈiːvəz bɪˈheɪvjə ɹisˈɑlɪks lˈaɪk ðə mˈɑdəl hˈæd lˈɚnd bˈeɪsɪks ˈæktɪs....
```

### Explanaition

| Generated IPA | Intended text             | Assessment                                                                    |
| ------------- | ------------------------- | ----------------------------------------------------------------------------- |
| ˈɪt           | It                        | ✓ Perfect                                                                     |
| gˈɪt          | gets                      | Very close (/ɛ/→/ɪ/, final /s/ lost)                                          |
| sˈʌbkəldz     | you past / past the cold- | This is where it still collapses several words together.                      |
| dˈɑɹk         | start                     | Still confuses **start** with **dark**.                                       |
| fˈeɪz         | phase                     | ✓ Excellent                                                                   |
| fˈæst         | fast                      | ✓ Perfect                                                                     |
| ðə            | The                       | ✓                                                                             |
| ɹˌɛpətˈɪʃən   | repetition                | ✓ Nearly perfect                                                              |
| luːp          | loop                      | ✓ Perfect                                                                     |
| nˈoʊ          | no                        | ✓                                                                             |
| ˈiːvəz        | EOS                       | Surprisingly close phonetically if the model has never seen "EOS" pronounced. |
| bɪˈheɪvjə     | behavior                  | ✓ Excellent                                                                   |
| ɹisˈɑlɪks     | we saw looks              | This is still garbled.                                                        |
| lˈaɪk ðə      | like the                  | ✓                                                                             |
| mˈɑdəl        | model                     | ✓ Perfect                                                                     |
| hˈæd          | hadn't                    | Lost the negation.                                                            |
| lˈɚnd         | learned                   | ✓                                                                             |
| bˈeɪsɪks      | basic                     | ✓                                                                             |
| ˈæktɪs        | mechanics                 | Still quite far.                                                              |



### End of training data:

Step 1185000 is chosen as this release

Step   | **WER**     | **CER**
-------|-------------|-------------
986000 | 80.65% | 36.93%
1148000 | 74.62% | 35.12%
1185000 | 73.00% | 33.88%
1202000 | 75.55% | 34.24%
1218000 | 74.28% | 35.23%