Downloads · 30 days
7
16% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-iv_hindi_vaani-62420-hinglish_mixed_scripts-alldata-1e-4-100-mix-0.7-FT
wav2vec2-large-xlsr-53-iv_hindi_vaani-62420-hinglish_mixed_scripts-alldata-1e-4-100-mix-0.7-FT is a automatic speech recognition model from dianavdavidson. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
7
16% of all-time downloads
All-time downloads
43
Public
Parameters
316M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Global Wer |
|---|---|---|---|---|
| 5.3864 | 1.0 | 1080 | 1.2860 | 71.2749 |
| 1.8811 | 2.0 | 2160 | 0.7792 | 46.8939 |
| 1.2819 | 3.0 | 3240 | 0.7485 | 42.3762 |
| 0.9941 | 4.0 | 4320 | 0.7515 | 39.5023 |
| 0.7947 | 5.0 | 5400 | 0.7995 | 39.1754 |
| 0.6454 | 6.0 | 6480 | 0.8076 | 39.2417 |
| 0.5037 | 7.0 | 7560 | 0.8401 | 37.8742 |
| 0.4562 | 8.0 | 8640 | 0.8517 | 37.3105 |
| 0.3874 | 9.0 | 9720 | 0.8537 | 37.5032 |
| 0.3358 | 10.0 | 10800 | 0.9138 | 37.1984 |
| 0.3088 | 11.0 | 11880 | 0.9843 | 37.1621 |
| 0.2667 | 12.0 | 12960 | 0.9849 | 36.5873 |
| 0.2372 | 13.0 | 14040 | 0.9620 | 36.7263 |
| 0.2187 | 14.0 | 15120 | 1.0223 | 37.0784 |
| 0.2097 | 15.0 | 16200 | 0.9390 | 36.6599 |