Downloads · 30 days
0
matcha-tts_ja_100speakers_group003f-CL-V2
Akjava/matcha-tts_ja_100speakers_group003f-CL-V2
matcha-tts_ja_100speakers_group003f-CL-V2 is a machine learning model from Akjava. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This model has 100 slots and 6 speaker use them <div class="audio-container" <h4ITA-Rectaion-010:家具商人のフィシェルは、荷車と仔馬を貸してくれた。(kagushooniNnofisheruwa,nigurumatokoumaokashItekureta.)</h4 <h5spk00:ja004</h5 <audio controls…
Access
Public
Updated Feb 7, 2026
Repo size
4.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.ckpt4.5 GB · 71%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 12, 2024
- Updated
- Feb 7, 2026
- SHA
- baa5bfa6
Base models
Datasets
Model card
From the Hugging Face model README
This model has 100 slots and 6 speaker use them
<div class="audio-container"> <h4>ITA-Rectaion-010:家具商人のフィシェルは、荷車と仔馬を貸してくれた。(kagushooniNnofisheruwa,nigurumatokoumaokashItekureta.)</h4> <h5>spk00:ja004</h5> <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2/resolve/main/examples/ita-recitation_group003f-v2_ep5709_spk00/utterance_010_speaker_000.wav "></audio> <h5>spk01:ja005</h5> <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2/resolve/main/examples/ita-recitation_group003f-v2_ep5709_spk01/utterance_010_speaker_001.wav "></audio> <h5>spk02:ja006</h5> <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2/resolve/main/examples/ita-recitation_group003f-v2_ep5709_spk02/utterance_010_speaker_002.wav "></audio> <h5>spk03:ja007</h5> <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2/resolve/main/examples/ita-recitation_group003f-v2_ep5709_spk03/utterance_010_speaker_003.wav "></audio> <h5>spk04:ja008</h5> <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2/resolve/main/examples/ita-recitation_group003f-v2_ep5709_spk04/utterance_010_speaker_004.wav "></audio> <h5>spk05:ja009</h5> <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2/resolve/main/examples/ita-recitation_group003f-v2_ep5709_spk05/utterance_010_speaker_005.wav "></audio> </div>Training
some how machine would freeze with 80 batch size ,change to 40
Stage1(2024-09-12_12-07-55)
maybe it need more training time,all voices are robotic
Stage2(2024-09-12_22-09-01)
most of them improved
spk0 - differenct intonation than v2
spk1 - v2 is better
spk2 - good
spk3 - good
spk4 - good
spk5 - Not so good .miss training dataset
Importan checkpoint
5709 - latest
- License
- mit
- Languages
- ja
- Created
- Sep 12, 2024
- Updated
- Feb 7, 2026