Text-to-Speech
English
Kokoro-82M / VOICES.md
hexgrad's picture
Upload 2 files
09f3623 verified
|
raw
history blame
5.64 kB
# Voices
For each voice, the given grades are intended to be estimates of the **quality and quantity** of its associated training data, both of which impact overall inference quality.
Subjectively, voices will sound better or worse to different people.
**Target Quality**
- How high quality is the reference voice? This grade may be impacted by audio quality, artifacts, compression, & sample rate.
- How well do the text labels match the audio? Text/audio misalignment (e.g. from hallucinations) will lower this grade.
**Training Duration**
- How much audio was seen during training? Smaller durations result in a lower overall grade.
- 10 hours <= HH hours < 100 hours
- 1 hour <= H hours < 10 hours
- 10 minutes <= MM minutes < 100 minutes
- 1 minute <= M minutes < 10 minutes
### American English ๐Ÿ‡บ๐Ÿ‡ธ
- [`misaki[en]`](https://github.com/hexgrad/misaki) `lang_code='a'` with `en-us` espeak-ng fallback
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ |
| af_alloy | ๐Ÿšบ | B | MM minutes | C | `6d877149` |
| af_aoede | ๐Ÿšบ | B | H hours | C+ | `c03bd1a4` |
| af_bella | ๐Ÿšบ๐Ÿ”ฅ | **A** | **HH hours** | **A-** | `8cb64e02` |
| af_jessica | ๐Ÿšบ | C | MM minutes | D | `cdfdccb8` |
| af_kore | ๐Ÿšบ | B | H hours | C+ | `8bfbc512` |
| af_nicole | ๐Ÿšบ๐ŸŽง | B | **HH hours** | B- | `c5561808` |
| af_nova | ๐Ÿšบ | B | MM minutes | C | `e0233676` |
| af_river | ๐Ÿšบ | C | MM minutes | D | `e149459b` |
| af_sarah | ๐Ÿšบ | B | H hours | C+ | `49bd364e` |
| af_sky | ๐Ÿšบ | B | M minutes | C- | `c799548a` |
| am_adam | ๐Ÿšน | D | H hours | F+ | `ced7e284` |
| am_echo | ๐Ÿšน | C | MM minutes | D | `8bcfdc85` |
| am_eric | ๐Ÿšน | C | MM minutes | D | `ada66f0e` |
| am_fenrir | ๐Ÿšน | B | H hours | C+ | `98e507ec` |
| am_liam | ๐Ÿšน | C | MM minutes | D | `c8255075` |
| am_michael | ๐Ÿšน | B | H hours | C+ | `9a443b79` |
| am_onyx | ๐Ÿšน | C | MM minutes | D | `e8452be1` |
| am_puck | ๐Ÿšน | B | H hours | C+ | `dd1d8973` |
### British English ๐Ÿ‡ฌ๐Ÿ‡ง
- [`misaki[en]`](https://github.com/hexgrad/misaki) `lang_code='b'` with `en-gb` espeak-ng fallback
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ |
| bf_alice | ๐Ÿšบ | C | MM minutes | D | `d292651b` |
| bf_emma | ๐Ÿšบ | B | **HH hours** | B- | `d0a423de` |
| bf_isabella | ๐Ÿšบ | B | MM minutes | C | `cdd4c370` |
| bf_lily | ๐Ÿšบ | C | MM minutes | D | `6e09c2e4` |
| bm_daniel | ๐Ÿšน | C | MM minutes | D | `fc3fce4e` |
| bm_fable | ๐Ÿšน | B | MM minutes | C | `d44935f3` |
| bm_george | ๐Ÿšน | B | MM minutes | C | `f1bc8122` |
| bm_lewis | ๐Ÿšน | C | H hours | D+ | `b5204750` |
### French ๐Ÿ‡ซ๐Ÿ‡ท
- espeak-ng `fr-fr`
- Total French training data: <11 hours
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 | CC BY |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ | ----- |
| ff_siwis | ๐Ÿšบ | B | <11 hours | B- | `8073bf2d` | [SIWIS](https://datashare.ed.ac.uk/handle/10283/2353) |
### Hindi ๐Ÿ‡ฎ๐Ÿ‡ณ
- espeak-ng `hi`
- Total Hindi training data: H hours
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ |
| hf_alpha | ๐Ÿšบ | B | MM minutes | C | `06906fe0` |
| hf_beta | ๐Ÿšบ | B | MM minutes | C | `63c0a1a6` |
| hm_omega | ๐Ÿšน | B | MM minutes | C | `b55f02a8` |
| hm_psi | ๐Ÿšน | B | MM minutes | C | `2f0f055c` |
### Italian ๐Ÿ‡ฎ๐Ÿ‡ณ
- espeak-ng `it`
- Total Italian training data: H hours
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ |
| if_sara | ๐Ÿšบ | B | MM minutes | C | `6c0b253b` |
| im_nicola | ๐Ÿšน | B | MM minutes | C | `234ed066` |
### Japanese ๐Ÿ‡ฏ๐Ÿ‡ต
- [`misaki[ja]`](https://github.com/hexgrad/misaki)
- Total Japanese training data: H hours
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 | CC BY |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ | ----- |
| jf_alpha | ๐Ÿšบ | B | H hours | C+ | `1bf4c9dc` | |
| jf_gongitsune | ๐Ÿšบ | B | MM minutes | C | `1b171917` | [gongitsune](https://github.com/koniwa/koniwa/blob/master/source/tnc/tnc__gongitsune.txt) |
| jf_nezumi | ๐Ÿšบ | B | M minutes | C- | `d83f007a` | [nezuminoyomeiri](https://github.com/koniwa/koniwa/blob/master/source/tnc/tnc__nezuminoyomeiri.txt) |
| jf_tebukuro | ๐Ÿšบ | B | MM minutes | C | `0d691790` | [tebukurowokaini](https://github.com/koniwa/koniwa/blob/master/source/tnc/tnc__tebukurowokaini.txt) |
| jm_kumo | ๐Ÿšน | B | M minutes | C- | `98340afd` | [kumonoito](https://github.com/koniwa/koniwa/blob/master/source/tnc/tnc__kumonoito.txt) |
### Mandarin Chinese ๐Ÿ‡จ๐Ÿ‡ณ
- [`misaki[zh]`](https://github.com/hexgrad/misaki)
- Total Mandarin Chinese training data: H hours
| Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 |
| ---- | ------ | -------------- | ----------------- | ------------- | ------ |
| zf_xiaobei | ๐Ÿšบ | C | MM minutes | D | `9b76be63` |
| zf_xiaoni | ๐Ÿšบ | C | MM minutes | D | `95b49f16` |
| zf_xiaoxiao | ๐Ÿšบ | C | MM minutes | D | `cfaf6f2d` |
| zf_xiaoyi | ๐Ÿšบ | C | MM minutes | D | `b5235dba` |
| zm_yunjian | ๐Ÿšน | C | MM minutes | D | `76cbf8ba` |
| zm_yunxi | ๐Ÿšน | C | MM minutes | D | `dbe6e1ce` |
| zm_yunxia | ๐Ÿšน | C | MM minutes | D | `bb2b03b0` |
| zm_yunyang | ๐Ÿšน | C | MM minutes | D | `5238ac22` |